-
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting
Authors:
Ching Ho Lee,
Javier Nistal,
Stefan Lattner,
Marco Pasini,
George Fazekas
Abstract:
We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise injection that targets latent channels most informative of instrument identity, and (ii) an early-step clamping mechanism that re-imposes the input's melodic an…
▽ More
We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise injection that targets latent channels most informative of instrument identity, and (ii) an early-step clamping mechanism that re-imposes the input's melodic and rhythmic structure during reverse diffusion. The method operates directly on audio latents and is compatible with text/audio conditioning (e.g., CLAP). We discuss design choices,analyze trade-offs between timbral change and structural preservation, and show that simple inference-time controls can meaningfully steer pre-trained models for style-transfer use cases.
△ Less
Submitted 28 January, 2026; v1 submitted 3 January, 2026;
originally announced January 2026.
-
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
Authors:
Mathias Rose Bjare,
Giorgia Cantisani,
Marco Pasini,
Stefan Lattner,
Gerhard Widmer
Abstract:
We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence of this hierarchical structure by showing that, after training an audio autoencoder in this manner, perceptually salient information is captured in coarser repr…
▽ More
We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence of this hierarchical structure by showing that, after training an audio autoencoder in this manner, perceptually salient information is captured in coarser representation structures than with conventional training. Furthermore, we show that such perceptual hierarchies improve latent diffusion decoding in the context of estimating surprisal in music pitches and predicting EEG-brain responses to music listening. Pretrained weights are available on github.com/CPJKU/pa-audioic.
△ Less
Submitted 10 November, 2025; v1 submitted 7 November, 2025;
originally announced November 2025.
-
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio
Authors:
Marco Pasini,
Stefan Lattner,
George Fazekas
Abstract:
Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving high compression ratios while maintaining audio fidelity remains a challenge. We introduce CoDiCodec, a novel audio autoencoder that overcomes these limitations…
▽ More
Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving high compression ratios while maintaining audio fidelity remains a challenge. We introduce CoDiCodec, a novel audio autoencoder that overcomes these limitations by both efficiently encoding global features via summary embeddings, and by producing both compressed continuous embeddings at ~ 11 Hz and discrete tokens at a rate of 2.38 kbps from the same trained model, offering unprecedented flexibility for different downstream generative tasks. This is achieved through Finite Scalar Quantization (FSQ) and a novel FSQ-dropout technique, and does not require additional loss terms beyond the single consistency loss used for end-to-end training. CoDiCodec supports both autoregressive decoding and a novel parallel decoding strategy, with the latter achieving superior audio quality and faster decoding. CoDiCodec outperforms existing continuous and discrete autoencoders at similar bitrates in terms of reconstruction audio quality. Our work enables a unified approach to audio compression, bridging the gap between continuous and discrete generative modelling paradigms.
△ Less
Submitted 11 September, 2025;
originally announced September 2025.
-
Estimating Musical Surprisal from Audio in Autoregressive Diffusion Model Noise Spaces
Authors:
Mathias Rose Bjare,
Stefan Lattner,
Gerhard Widmer
Abstract:
Recently, the information content (IC) of predictions from a Generative Infinite-Vocabulary Transformer (GIVT) has been used to model musical expectancy and surprisal in audio. We investigate the effectiveness of such modelling using IC calculated with autoregressive diffusion models (ADMs). We empirically show that IC estimates of models based on two different diffusion ordinary differential equa…
▽ More
Recently, the information content (IC) of predictions from a Generative Infinite-Vocabulary Transformer (GIVT) has been used to model musical expectancy and surprisal in audio. We investigate the effectiveness of such modelling using IC calculated with autoregressive diffusion models (ADMs). We empirically show that IC estimates of models based on two different diffusion ordinary differential equations (ODEs) describe diverse data better, in terms of negative log-likelihood, than a GIVT. We evaluate diffusion model IC's effectiveness in capturing surprisal aspects by examining two tasks: (1) capturing monophonic pitch surprisal, and (2) detecting segment boundaries in multi-track audio. In both tasks, the diffusion models match or exceed the performance of a GIVT. We hypothesize that the surprisal estimated at different diffusion process noise levels corresponds to the surprisal of music and audio features present at different audio granularities. Testing our hypothesis, we find that, for appropriate noise levels, the studied musical surprisal tasks' results improve. Code is provided on github.com/SonyCSLParis/audioic.
△ Less
Submitted 7 August, 2025;
originally announced August 2025.
-
PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
Authors:
Alain Riou,
Bernardo Torres,
Ben Hayes,
Stefan Lattner,
Gaëtan Hadjeres,
Gaël Richard,
Geoffroy Peeters
Abstract:
In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable-$Q$ Transform (VQT) and predicts pitch distributions. The neural network is designed to be equivariant to translations, notably thanks to a Toeplitz fully-connected layer. In addition, we construct pitch-shifted pairs b…
▽ More
In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable-$Q$ Transform (VQT) and predicts pitch distributions. The neural network is designed to be equivariant to translations, notably thanks to a Toeplitz fully-connected layer. In addition, we construct pitch-shifted pairs by translating and cropping the VQT frames and train our model with a novel class-based transposition-equivariant objective, eliminating the need for annotated data. Thanks to this architecture and training objective, our model achieves remarkable performances while being very lightweight ($130$k parameters). Evaluations on music and speech datasets (MIR-1K, MDB-stem-synth, and PTDB) demonstrate that PESTO not only outperforms self-supervised baselines but also competes with supervised methods, exhibiting superior cross-dataset generalization. Finally, we enhance PESTO's practical utility by developing a streamable VQT implementation using cached convolutions. Combined with our model's low latency (less than 10 ms) and minimal parameter count, this makes PESTO particularly suitable for real-time applications.
△ Less
Submitted 27 October, 2025; v1 submitted 2 August, 2025;
originally announced August 2025.
-
Assessing the Alignment of Audio Representations with Timbre Similarity Ratings
Authors:
Haokun Tian,
Stefan Lattner,
Charalampos Saitis
Abstract:
Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent results from audio (music and speech) quality assessment as well as image similarity have shown that deep learning is able to produce embeddings that align well…
▽ More
Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent results from audio (music and speech) quality assessment as well as image similarity have shown that deep learning is able to produce embeddings that align well with human perception while being largely free from these constraints. Although the existing human-rated timbre similarity data is not large enough to train deep neural networks (2,614 pairwise ratings on 334 audio samples), it can serve as test-only data for audio models. In this paper, we introduce metrics to assess the alignment of diverse audio representations with human judgments of timbre similarity by comparing both the absolute values and the rankings of embedding distances to human similarity ratings. Our evaluation involves three signal-processing-based representations, twelve representations extracted from pre-trained models, and three representations extracted from a novel sound matching model. Among them, the style embeddings inspired by image style transfer, extracted from the CLAP model and the sound matching model, remarkably outperform the others, showing their potential in modeling timbre similarity.
△ Less
Submitted 10 July, 2025;
originally announced July 2025.
-
Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding
Authors:
Marco Pasini,
Stefan Lattner,
George Fazekas
Abstract:
Efficiently compressing high-dimensional audio signals into a compact and informative latent space is crucial for various tasks, including generative modeling and music information retrieval (MIR). Existing audio autoencoders, however, often struggle to achieve high compression ratios while preserving audio fidelity and facilitating efficient downstream applications. We introduce Music2Latent2, a…
▽ More
Efficiently compressing high-dimensional audio signals into a compact and informative latent space is crucial for various tasks, including generative modeling and music information retrieval (MIR). Existing audio autoencoders, however, often struggle to achieve high compression ratios while preserving audio fidelity and facilitating efficient downstream applications. We introduce Music2Latent2, a novel audio autoencoder that addresses these limitations by leveraging consistency models and a novel approach to representation learning based on unordered latent embeddings, which we call summary embeddings. Unlike conventional methods that encode local audio features into ordered sequences, Music2Latent2 compresses audio signals into sets of summary embeddings, where each embedding can capture distinct global features of the input sample. This enables to achieve higher reconstruction quality at the same compression ratio. To handle arbitrary audio lengths, Music2Latent2 employs an autoregressive consistency model trained on two consecutive audio chunks with causal masking, ensuring coherent reconstruction across segment boundaries. Additionally, we propose a novel two-step decoding procedure that leverages the denoising capabilities of consistency models to further refine the generated audio at no additional cost. Our experiments demonstrate that Music2Latent2 outperforms existing continuous audio autoencoders regarding audio quality and performance on downstream tasks. Music2Latent2 paves the way for new possibilities in audio compression.
△ Less
Submitted 29 January, 2025;
originally announced January 2025.
-
Hybrid Losses for Hierarchical Embedding Learning
Authors:
Haokun Tian,
Stefan Lattner,
Brian McFee,
Charalampos Saitis
Abstract:
In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By leveraging a tree hierarchy for fine-grained labels, we investigate hybrid losses, such as generalised triplet and cross-entropy losses, to enforce similarity between labels within a multi-task learning framework. We prop…
▽ More
In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By leveraging a tree hierarchy for fine-grained labels, we investigate hybrid losses, such as generalised triplet and cross-entropy losses, to enforce similarity between labels within a multi-task learning framework. We propose metrics to evaluate the embedding space structure and assess the model's ability to generalise to unseen classes, that is, to infer similar classes for data belonging to unseen categories. Our experiments on OrchideaSOL, a four-level hierarchical instrument sound dataset with nearly 200 detailed categories, demonstrate that the proposed hybrid losses outperform previous works in classification, retrieval, embedding space structure, and generalisation.
△ Less
Submitted 22 January, 2025;
originally announced January 2025.
-
Estimating Musical Surprisal in Audio
Authors:
Mathias Rose Bjare,
Giorgia Cantisani,
Stefan Lattner,
Gerhard Widmer
Abstract:
In modeling musical surprisal expectancy with computational methods, it has been proposed to use the information content (IC) of one-step predictions from an autoregressive model as a proxy for surprisal in symbolic music. With an appropriately chosen model, the IC of musical events has been shown to correlate with human perception of surprise and complexity aspects, including tonal and rhythmic c…
▽ More
In modeling musical surprisal expectancy with computational methods, it has been proposed to use the information content (IC) of one-step predictions from an autoregressive model as a proxy for surprisal in symbolic music. With an appropriately chosen model, the IC of musical events has been shown to correlate with human perception of surprise and complexity aspects, including tonal and rhythmic complexity. This work investigates whether an analogous methodology can be applied to music audio. We train an autoregressive Transformer model to predict compressed latent audio representations of a pretrained autoencoder network. We verify learning effects by estimating the decrease in IC with repetitions. We investigate the mean IC of musical segment types (e.g., A or B) and find that segment types appearing later in a piece have a higher IC than earlier ones on average. We investigate the IC's relation to audio and musical features and find it correlated with timbral variations and loudness and, to a lesser extent, dissonance, rhythmic complexity, and onset density related to audio and musical features. Finally, we investigate if the IC can predict EEG responses to songs and thus model humans' surprisal in music. We provide code for our method on github.com/sonycslparis/audioic.
△ Less
Submitted 13 January, 2025;
originally announced January 2025.
-
Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures
Authors:
Alain Riou,
Antonin Gagneré,
Gaëtan Hadjeres,
Stefan Lattner,
Geoffroy Peeters
Abstract:
In this paper, we tackle the task of musical stem retrieval. Given a musical mix, it consists in retrieving a stem that would fit with it, i.e., that would sound pleasant if played together. To do so, we introduce a new method based on Joint-Embedding Predictive Architectures, where an encoder and a predictor are jointly trained to produce latent representations of a context and predict latent rep…
▽ More
In this paper, we tackle the task of musical stem retrieval. Given a musical mix, it consists in retrieving a stem that would fit with it, i.e., that would sound pleasant if played together. To do so, we introduce a new method based on Joint-Embedding Predictive Architectures, where an encoder and a predictor are jointly trained to produce latent representations of a context and predict latent representations of a target. In particular, we design our predictor to be conditioned on arbitrary instruments, enabling our model to perform zero-shot stem retrieval. In addition, we discover that pretraining the encoder using contrastive learning drastically improves the model's performance.
We validate the retrieval performances of our model using the MUSDB18 and MoisesDB datasets. We show that it significantly outperforms previous baselines on both datasets, showcasing its ability to support more or less precise (and possibly unseen) conditioning. We also evaluate the learned embeddings on a beat tracking task, demonstrating that they retain temporal structure and local information.
△ Less
Submitted 24 February, 2025; v1 submitted 29 November, 2024;
originally announced November 2024.
-
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation
Authors:
Marco Pasini,
Javier Nistal,
Stefan Lattner,
George Fazekas
Abstract:
Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive manner is also feasible. However, such Continuous Autoregressive Models (CAMs) can suffer from a decline in generation quality over extended sequences due to error accumulation during inference. We introduce a novel metho…
▽ More
Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive manner is also feasible. However, such Continuous Autoregressive Models (CAMs) can suffer from a decline in generation quality over extended sequences due to error accumulation during inference. We introduce a novel method to address this issue by injecting random noise into the input embeddings during training. This procedure makes the model robust against varying error levels at inference. We further reduce error accumulation through an inference procedure that introduces low-level noise. Experiments on musical audio generation show that CAM substantially outperforms existing autoregressive and non-autoregressive approaches while preserving audio quality over extended sequences. This work paves the way for generating continuous embeddings in a purely autoregressive setting, opening new possibilities for real-time and interactive generative applications.
△ Less
Submitted 27 November, 2024;
originally announced November 2024.
-
Improving Musical Accompaniment Co-creation via Diffusion Transformers
Authors:
Javier Nistal,
Marco Pasini,
Stefan Lattner
Abstract:
Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the underlying autoencoder to a stereo-capable model with superior fidelity and replace the latent U-Net with a Diffusion Transformer. Additionally, we refine text prompting…
▽ More
Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the underlying autoencoder to a stereo-capable model with superior fidelity and replace the latent U-Net with a Diffusion Transformer. Additionally, we refine text prompting by training a cross-modality predictive network to translate text-derived CLAP embeddings to audio-derived CLAP embeddings. Finally, we improve inference speed by training the latent model using a consistency framework, achieving competitive quality with fewer denoising steps. Our model is evaluated against the original Diff-A-Riff variant using objective metrics in ablation experiments, demonstrating promising advancements in all targeted areas. Sound examples are available at: https://sonycslparis.github.io/improved_dar/.
△ Less
Submitted 30 October, 2024;
originally announced October 2024.
-
The evolution of inharmonicity and noisiness in contemporary popular music
Authors:
Emmanuel Deruty,
David Meredith,
Stefan Lattner
Abstract:
Much of Western classical music relies on instruments based on acoustic resonance, which produce harmonic or quasi-harmonic sounds. In contrast, since the mid-twentieth century, popular music has increasingly been produced in recording studios, where it is not bound by the constraints of harmonic sounds. In this study, we use modified MPEG-7 features to explore and characterise the evolution of no…
▽ More
Much of Western classical music relies on instruments based on acoustic resonance, which produce harmonic or quasi-harmonic sounds. In contrast, since the mid-twentieth century, popular music has increasingly been produced in recording studios, where it is not bound by the constraints of harmonic sounds. In this study, we use modified MPEG-7 features to explore and characterise the evolution of noise and inharmonicity in popular music since 1961. We place this evolution in the context of other broad categories of music, including Western classical piano music, orchestral music, and musique concrète. We introduce new features that distinguish between inharmonicity caused by noise and that resulting from interactions between discrete partials. Our analysis reveals that the history of popular music since 1961 can be divided into three phases. From 1961 to 1972, inharmonicity in popular music, initially only slightly higher than in orchestral music, increased significantly. Between 1972 and 1986, this rise in inharmonicity was accompanied by an increase in noise, but since 1986, both inharmonicity and noise have moderately decreased. In recent years (up to 2020), popular music has remained much more inharmonic than popular music from the 1960s or orchestral music involving acoustic resonance instruments. However, it has become less noisy, with noise levels comparable to those of orchestral music. We relate these trends to the evolution of music production techniques. In particular, the use of multi-tracking may explain the higher inharmonicity in popular music compared to orchestral music. We illustrate these trends with analyses of key artists and tracks.
△ Less
Submitted 6 December, 2024; v1 submitted 15 August, 2024;
originally announced August 2024.
-
Music2Latent: Consistency Autoencoders for Latent Audio Compression
Authors:
Marco Pasini,
Stefan Lattner,
George Fazekas
Abstract:
Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by…
▽ More
Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by leveraging consistency models. Music2Latent encodes samples into a compressed continuous latent space in a single end-to-end training process while enabling high-fidelity single-step reconstruction. Key innovations include conditioning the consistency model on upsampled encoder outputs at all levels through cross connections, using frequency-wise self-attention to capture long-range frequency dependencies, and employing frequency-wise learned scaling to handle varying value distributions across frequencies at different noise levels. We demonstrate that Music2Latent outperforms existing continuous audio autoencoders in sound quality and reconstruction accuracy while achieving competitive performance on downstream MIR tasks using its latent representations. To our knowledge, this represents the first successful attempt at training an end-to-end consistency autoencoder model.
△ Less
Submitted 12 August, 2024;
originally announced August 2024.
-
Controlling Surprisal in Music Generation via Information Content Curve Matching
Authors:
Mathias Rose Bjare,
Stefan Lattner,
Gerhard Widmer
Abstract:
In recent years, the quality and public interest in music generation systems have grown, encouraging research into various ways to control these systems. We propose a novel method for controlling surprisal in music generation using sequence models. To achieve this goal, we define a metric called Instantaneous Information Content (IIC). The IIC serves as a proxy function for the perceived musical s…
▽ More
In recent years, the quality and public interest in music generation systems have grown, encouraging research into various ways to control these systems. We propose a novel method for controlling surprisal in music generation using sequence models. To achieve this goal, we define a metric called Instantaneous Information Content (IIC). The IIC serves as a proxy function for the perceived musical surprisal (as estimated from a probabilistic model) and can be calculated at any point within a music piece. This enables the comparison of surprisal across different musical content even if the musical events occur in irregular time intervals. We use beam search to generate musical material whose IIC curve closely approximates a given target IIC. We experimentally show that the IIC correlates with harmonic and rhythmic complexity and note density. The correlation decreases with the length of the musical context used for estimating the IIC. Finally, we conduct a qualitative user study to test if human listeners can identify the IIC curves that have been used as targets when generating the respective musical material. We provide code for creating IIC interpolations and IIC visualizations on https://github.com/muthissar/iic.
△ Less
Submitted 12 August, 2024;
originally announced August 2024.
-
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
Authors:
Alain Riou,
Stefan Lattner,
Gaëtan Hadjeres,
Michael Anslow,
Geoffroy Peeters
Abstract:
This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Predictive Architecture (JEPA) trained on a multi-track dataset using a self-supervised learning approach.
Our model comprises two networks: an encode…
▽ More
This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Predictive Architecture (JEPA) trained on a multi-track dataset using a self-supervised learning approach.
Our model comprises two networks: an encoder and a predictor, which are jointly trained to predict the embeddings of compatible stems from the embeddings of a given context, typically a mix of several instruments. Training a model in this manner allows its use in estimating stem compatibility - retrieving, aligning, or generating a stem to match a given mix - or for downstream tasks such as genre or key estimation, as the training paradigm requires the model to learn information related to timbre, harmony, and rhythm.
We evaluate our model's performance on a retrieval task on the MUSDB18 dataset, testing its ability to find the missing stem from a mix and through a subjective user study. We also show that the learned embeddings capture temporal alignment information and, finally, evaluate the representations learned by our model on several downstream tasks, highlighting that they effectively capture meaningful musical features.
△ Less
Submitted 5 August, 2024;
originally announced August 2024.
-
Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models
Authors:
Javier Nistal,
Marco Pasini,
Cyran Aouameur,
Maarten Grachten,
Stefan Lattner
Abstract:
Recent advancements in deep generative models present new opportunities for music production but also pose challenges, such as high computational demands and limited audio quality. Moreover, current systems frequently rely solely on text input and typically focus on producing complete musical pieces, which is incompatible with existing workflows in music production. To address these issues, we int…
▽ More
Recent advancements in deep generative models present new opportunities for music production but also pose challenges, such as high computational demands and limited audio quality. Moreover, current systems frequently rely solely on text input and typically focus on producing complete musical pieces, which is incompatible with existing workflows in music production. To address these issues, we introduce "Diff-A-Riff," a Latent Diffusion Model designed to generate high-quality instrumental accompaniments adaptable to any musical context. This model offers control through either audio references, text prompts, or both, and produces 48kHz pseudo-stereo audio while significantly reducing inference time and memory usage. We demonstrate the model's capabilities through objective metrics and subjective listening tests, with extensive examples available on the accompanying website: sonycslparis.github.io/diffariff-companion/
△ Less
Submitted 30 October, 2024; v1 submitted 12 June, 2024;
originally announced June 2024.
-
Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning
Authors:
Alain Riou,
Stefan Lattner,
Gaëtan Hadjeres,
Geoffroy Peeters
Abstract:
This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram into two parts (context and target), computing neural representations for each, and training the neural network to predict the target representations from the cont…
▽ More
This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram into two parts (context and target), computing neural representations for each, and training the neural network to predict the target representations from the context representations. We investigate several design choices within this framework and study their influence through extensive experiments by evaluating our models on various audio classification benchmarks, including environmental sounds, speech and music downstream tasks. We focus notably on which part of the input data is used as context or target and show experimentally that it significantly impacts the model's quality. In particular, we notice that some effective design choices in the image domain lead to poor performance on audio, thus highlighting major differences between these two modalities.
△ Less
Submitted 14 May, 2024;
originally announced May 2024.
-
Bass Accompaniment Generation via Latent Diffusion
Authors:
Marco Pasini,
Maarten Grachten,
Stefan Lattner
Abstract:
The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent dif…
▽ More
The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent diffusion model that takes as input the latent encoding of a mix and generates the latent encoding of a corresponding stem. To provide control over the timbre of generated samples, we introduce a technique to ground the latent space to a user-provided reference style during diffusion sampling. For further improving audio quality, we adapt classifier-free guidance to avoid distortions at high guidance strengths when generating an unbounded latent space. We train our model on a dataset of pairs of mixes and matching bass stems. Quantitative experiments demonstrate that, given an input mix, the proposed system can generate basslines with user-specified timbres. Our controllable conditional audio generation framework represents a significant step forward in creating generative AI tools to assist musicians in music production.
△ Less
Submitted 2 February, 2024;
originally announced February 2024.
-
Singer Identity Representation Learning using Self-Supervised Techniques
Authors:
Bernardo Torres,
Stefan Lattner,
Gaël Richard
Abstract:
Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer identity encoders to extract representations suitable for various singing-related tasks, such as singing voice similarity and synthesis. We explore different self…
▽ More
Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer identity encoders to extract representations suitable for various singing-related tasks, such as singing voice similarity and synthesis. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks and apply data augmentations during training to ensure that the representations are invariant to pitch and content variations. We evaluate the quality of the resulting representations on singer similarity and identification tasks across multiple datasets, with a particular emphasis on out-of-domain generalization. Our proposed framework produces high-quality embeddings that outperform both speaker verification and wav2vec 2.0 pre-trained baselines on singing voice while operating at 44.1 kHz. We release our code and trained models to facilitate further research on singing voice and related areas.
△ Less
Submitted 10 January, 2024;
originally announced January 2024.
-
Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates
Authors:
Marco Pasini,
Stefan Lattner,
George Fazekas
Abstract:
Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its diversity. More recent methods have delved into N-shot techniques that utilize one or more audio samples to aid in the separation. However, a challenge with some of…
▽ More
Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its diversity. More recent methods have delved into N-shot techniques that utilize one or more audio samples to aid in the separation. However, a challenge with some of these methods is the necessity for an audio query during inference, making them less suited for genres with varied timbres and effects. This paper offers a proof-of-concept for a self-supervised music source separation system that eliminates the need for audio queries at inference time. In the training phase, while it adopts a query-based approach, we introduce a modification by substituting the continuous embedding of query audios with Vector Quantized (VQ) representations. Trained end-to-end with up to N classes as determined by the VQ's codebook size, the model seeks to effectively categorise instrument classes. During inference, the input is partitioned into N sources, with some potentially left unutilized based on the mix's instrument makeup. This methodology suggests an alternative avenue for considering source separation across diverse music genres. We provide examples and additional results online.
△ Less
Submitted 21 November, 2023;
originally announced November 2023.
-
PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective
Authors:
Alain Riou,
Stefan Lattner,
Gaëtan Hadjeres,
Geoffroy Peeters
Abstract:
In this paper, we address the problem of pitch estimation using Self Supervised Learning (SSL). The SSL paradigm we use is equivariance to pitch transposition, which enables our model to accurately perform pitch estimation on monophonic audio after being trained only on a small unlabeled dataset. We use a lightweight ($<$ 30k parameters) Siamese neural network that takes as inputs two different pi…
▽ More
In this paper, we address the problem of pitch estimation using Self Supervised Learning (SSL). The SSL paradigm we use is equivariance to pitch transposition, which enables our model to accurately perform pitch estimation on monophonic audio after being trained only on a small unlabeled dataset. We use a lightweight ($<$ 30k parameters) Siamese neural network that takes as inputs two different pitch-shifted versions of the same audio represented by its Constant-Q Transform. To prevent the model from collapsing in an encoder-only setting, we propose a novel class-based transposition-equivariant objective which captures pitch information. Furthermore, we design the architecture of our network to be transposition-preserving by introducing learnable Toeplitz matrices.
We evaluate our model for the two tasks of singing voice and musical instrument pitch estimation and show that our model is able to generalize across tasks and datasets while being lightweight, hence remaining compatible with low-resource devices and suitable for real-time applications. In particular, our results surpass self-supervised baselines and narrow the performance gap between self-supervised and supervised methods for pitch estimation.
△ Less
Submitted 27 October, 2025; v1 submitted 5 September, 2023;
originally announced September 2023.
-
Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model
Authors:
Mathias Rose Bjare,
Stefan Lattner,
Gerhard Widmer
Abstract:
Research in natural language processing has demonstrated that the quality of generations from trained autoregressive language models is significantly influenced by the used sampling strategy. In this study, we investigate the impact of different sampling techniques on musical qualities such as diversity and structure. To accomplish this, we train a high-capacity transformer model on a vast collect…
▽ More
Research in natural language processing has demonstrated that the quality of generations from trained autoregressive language models is significantly influenced by the used sampling strategy. In this study, we investigate the impact of different sampling techniques on musical qualities such as diversity and structure. To accomplish this, we train a high-capacity transformer model on a vast collection of highly-structured Irish folk melodies and analyze the musical qualities of the samples generated using distribution truncation sampling techniques. Specifically, we use nucleus sampling, the recently proposed "typical sampling", and conventional ancestral sampling. We evaluate the effect of these sampling strategies in two scenarios: optimal circumstances with a well-calibrated model and suboptimal circumstances where we systematically degrade the model's performance. We assess the generated samples using objective and subjective evaluations. We discover that probability truncation techniques may restrict diversity and structural patterns in optimal circumstances, but may also produce more musical samples in suboptimal circumstances.
△ Less
Submitted 18 August, 2023;
originally announced August 2023.
-
On the Typicality of Musical Sequences
Authors:
Mathias Rose Bjare,
Stefan Lattner
Abstract:
It has been shown in a recent publication that words in human-produced English language tend to have an information content close to the conditional entropy. In this paper, we show that the same is true for events in human-produced monophonic musical sequences. We also show how "typical sampling" influences the distribution of information around the entropy for single events and sequences.
It has been shown in a recent publication that words in human-produced English language tend to have an information content close to the conditional entropy. In this paper, we show that the same is true for events in human-produced monophonic musical sequences. We also show how "typical sampling" influences the distribution of information around the entropy for single events and sequences.
△ Less
Submitted 23 November, 2022;
originally announced November 2022.
-
SampleMatch: Drum Sample Retrieval by Musical Context
Authors:
Stefan Lattner
Abstract:
Modern digital music production typically involves combining numerous acoustic elements to compile a piece of music. Important types of such elements are drum samples, which determine the characteristics of the percussive components of the piece. Artists must use their aesthetic judgement to assess whether a given drum sample fits the current musical context. However, selecting drum samples from a…
▽ More
Modern digital music production typically involves combining numerous acoustic elements to compile a piece of music. Important types of such elements are drum samples, which determine the characteristics of the percussive components of the piece. Artists must use their aesthetic judgement to assess whether a given drum sample fits the current musical context. However, selecting drum samples from a potentially large library is tedious and may interrupt the creative flow. In this work, we explore the automatic drum sample retrieval based on aesthetic principles learned from data. As a result, artists can rank the samples in their library by fit to some musical context at different stages of the production process (i.e., by fit to incomplete song mixtures). To this end, we use contrastive learning to maximize the score of drum samples originating from the same song as the mixture. We conduct a listening test to determine whether the human ratings match the automatic scoring function. We also perform objective quantitative analyses to evaluate the efficacy of our approach.
△ Less
Submitted 1 August, 2022;
originally announced August 2022.
-
Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks
Authors:
Stefan Lattner,
Javier Nistal
Abstract:
Lossy audio codecs compress (and decompress) digital audio streams by removing information that tends to be inaudible in human perception. Under high compression rates, such codecs may introduce a variety of impairments in the audio signal. Many works have tackled the problem of audio enhancement and compression artifact removal using deep learning techniques. However, only a few works tackle the…
▽ More
Lossy audio codecs compress (and decompress) digital audio streams by removing information that tends to be inaudible in human perception. Under high compression rates, such codecs may introduce a variety of impairments in the audio signal. Many works have tackled the problem of audio enhancement and compression artifact removal using deep learning techniques. However, only a few works tackle the restoration of heavily compressed audio signals in the musical domain. In such a scenario, there is no unique solution for the restoration of the original signal. Therefore, in this study, we test a stochastic generator of a Generative Adversarial Network (GAN) architecture for this task. Such a stochastic generator, conditioned on highly compressed musical audio signals, could one day generate outputs indistinguishable from high-quality releases. Therefore, the present study may yield insights into more efficient musical data storage and transmission. We train stochastic and deterministic generators on MP3-compressed audio signals with 16, 32, and 64 kbit/s. We perform an extensive evaluation of the different experiments utilizing objective metrics and listening tests. We find that the models can improve the quality of the audio signals over the MP3 versions for 16 and 32 kbit/s and that the stochastic generators are capable of generating outputs that are closer to the original signals than those of the deterministic generators.
△ Less
Submitted 4 July, 2022;
originally announced July 2022.
-
DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis With Autoencoding Generative Adversarial Networks
Authors:
Javier Nistal,
Cyran Aouameur,
Ithan Velarde,
Stefan Lattner
Abstract:
In contemporary popular music production, drum sound design is commonly performed by cumbersome browsing and processing of pre-recorded samples in sound libraries. One can also use specialized synthesis hardware, typically controlled through low-level, musically meaningless parameters. Today, the field of Deep Learning offers methods to control the synthesis process via learned high-level features…
▽ More
In contemporary popular music production, drum sound design is commonly performed by cumbersome browsing and processing of pre-recorded samples in sound libraries. One can also use specialized synthesis hardware, typically controlled through low-level, musically meaningless parameters. Today, the field of Deep Learning offers methods to control the synthesis process via learned high-level features and allows generating a wide variety of sounds. In this paper, we present DrumGAN VST, a plugin for synthesizing drum sounds using a Generative Adversarial Network. DrumGAN VST operates on 44.1 kHz sample-rate audio, offers independent and continuous instrument class controls, and features an encoding neural network that maps sounds into the GAN's latent space, enabling resynthesis and manipulation of pre-existing drum sounds. We provide numerous sound examples and a demo of the proposed VST plugin.
△ Less
Submitted 29 June, 2022;
originally announced June 2022.
-
DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
Authors:
Javier Nistal,
Stefan Lattner,
Gaël Richard
Abstract:
Generative Adversarial Networks (GANs) have achieved excellent audio synthesis quality in the last years. However, making them operable with semantically meaningful controls remains an open challenge. An obvious approach is to control the GAN by conditioning it on metadata contained in audio datasets. Unfortunately, audio datasets often lack the desired annotations, especially in the musical domai…
▽ More
Generative Adversarial Networks (GANs) have achieved excellent audio synthesis quality in the last years. However, making them operable with semantically meaningful controls remains an open challenge. An obvious approach is to control the GAN by conditioning it on metadata contained in audio datasets. Unfortunately, audio datasets often lack the desired annotations, especially in the musical domain. A way to circumvent this lack of annotations is to generate them, for example, with an automatic audio-tagging system. The output probabilities of such systems (so-called "soft labels") carry rich information about the characteristics of the respective audios and can be used to distill the knowledge from a teacher model into a student model. In this work, we perform knowledge distillation from a large audio tagging system into an adversarial audio synthesizer that we call DarkGAN. Results show that DarkGAN can synthesize musical audio with acceptable quality and exhibits moderate attribute control even with out-of-distribution input conditioning. We release the code and provide audio examples on the accompanying website.
△ Less
Submitted 2 August, 2021;
originally announced August 2021.
-
VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding
Authors:
Javier Nistal,
Cyran Aouameur,
Stefan Lattner,
Gaël Richard
Abstract:
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the (musical) audio domain, it is often desired to generate output of variable duration. This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio…
▽ More
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the (musical) audio domain, it is often desired to generate output of variable duration. This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio by exploiting Vector-Quantized Contrastive Predictive Coding (VQCPC). A sequence of VQCPC tokens extracted from real audio data serves as conditional input to a GAN architecture, providing step-wise time-dependent features of the generated content. The input noise z (characteristic in adversarial architectures) remains fixed over time, ensuring temporal consistency of global features. We evaluate the proposed model by comparing a diverse set of metrics against various strong baselines. Results show that, even though the baselines score best, VQCPC-GAN achieves comparable performance even when generating variable-length audio. Numerous sound examples are provided in the accompanying website, and we release the code for reproducibility.
△ Less
Submitted 30 July, 2021; v1 submitted 4 May, 2021;
originally announced May 2021.
-
DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks
Authors:
J. Nistal,
S. Lattner,
G. Richard
Abstract:
Synthetic creation of drum sounds (e.g., in drum machines) is commonly performed using analog or digital synthesis, allowing a musician to sculpt the desired timbre modifying various parameters. Typically, such parameters control low-level features of the sound and often have no musical meaning or perceptual correspondence. With the rise of Deep Learning, data-driven processing of audio emerges as…
▽ More
Synthetic creation of drum sounds (e.g., in drum machines) is commonly performed using analog or digital synthesis, allowing a musician to sculpt the desired timbre modifying various parameters. Typically, such parameters control low-level features of the sound and often have no musical meaning or perceptual correspondence. With the rise of Deep Learning, data-driven processing of audio emerges as an alternative to traditional signal processing. This new paradigm allows controlling the synthesis process through learned high-level features or by conditioning a model on musically relevant information. In this paper, we apply a Generative Adversarial Network to the task of audio synthesis of drum sounds. By conditioning the model on perceptual features computed with a publicly available feature-extractor, intuitive control is gained over the generation process. The experiments are carried out on a large collection of kick, snare, and cymbal sounds. We show that, compared to a specific prior work based on a U-Net architecture, our approach considerably improves the quality of the generated drum samples, and that the conditional input indeed shapes the perceptual characteristics of the sounds. Also, we provide audio examples and release the code used in our experiments.
△ Less
Submitted 28 June, 2022; v1 submitted 27 August, 2020;
originally announced August 2020.
-
Comparing Representations for Audio Synthesis Using Generative Adversarial Networks
Authors:
Javier Nistal,
Stefan Lattner,
Gaël Richard
Abstract:
In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the experiments on a subset of the NSynth dataset. The architecture follows the benchmark Progressive Growing Wasserstein GAN. We perform experiments both in a full…
▽ More
In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the experiments on a subset of the NSynth dataset. The architecture follows the benchmark Progressive Growing Wasserstein GAN. We perform experiments both in a fully non-conditional manner as well as conditioning the network on the pitch information. We quantitatively evaluate the generated material utilizing standard metrics for assessing generative models, and compare training and sampling times. We show that complex-valued as well as the magnitude and Instantaneous Frequency of the Short-Time Fourier Transform achieve the best results, and yield fast generation and inversion times. The code for feature extraction, training and evaluating the model is available online.
△ Less
Submitted 17 June, 2020; v1 submitted 16 June, 2020;
originally announced June 2020.
-
Modeling Musical Structure with Artificial Neural Networks
Authors:
Stefan Lattner
Abstract:
In recent years, artificial neural networks (ANNs) have become a universal tool for tackling real-world problems. ANNs have also shown great success in music-related tasks including music summarization and classification, similarity estimation, computer-aided or autonomous composition, and automatic music analysis. As structure is a fundamental characteristic of Western music, it plays a role in a…
▽ More
In recent years, artificial neural networks (ANNs) have become a universal tool for tackling real-world problems. ANNs have also shown great success in music-related tasks including music summarization and classification, similarity estimation, computer-aided or autonomous composition, and automatic music analysis. As structure is a fundamental characteristic of Western music, it plays a role in all these tasks. Some structural aspects are particularly challenging to learn with current ANN architectures. This is especially true for mid- and high-level self-similarity, tonal and rhythmic relationships. In this thesis, I explore the application of ANNs to different aspects of musical structure modeling, identify some challenges involved and propose strategies to address them. First, using probability estimations of a Restricted Boltzmann Machine (RBM), a probabilistic bottom-up approach to melody segmentation is studied. Then, a top-down method for imposing a high-level structural template in music generation is presented, which combines Gibbs sampling using a convolutional RBM with gradient-descent optimization on the intermediate solutions. Furthermore, I motivate the relevance of musical transformations in structure modeling and show how a connectionist model, the Gated Autoencoder (GAE), can be employed to learn transformations between musical fragments. For learning transformations in sequences, I propose a special predictive training of the GAE, which yields a representation of polyphonic music as a sequence of intervals. Furthermore, the applicability of these interval representations to a top-down discovery of repeated musical sections is shown. Finally, a recurrent variant of the GAE is proposed, and its efficacy in music prediction and modeling of low-level repetition structure is demonstrated.
△ Less
Submitted 6 January, 2020;
originally announced January 2020.
-
High-Level Control of Drum Track Generation Using Learned Patterns of Rhythmic Interaction
Authors:
Stefan Lattner,
Maarten Grachten
Abstract:
Spurred by the potential of deep learning, computational music generation has gained renewed academic interest. A crucial issue in music generation is that of user control, especially in scenarios where the music generation process is conditioned on existing musical material. Here we propose a model for conditional kick drum track generation that takes existing musical material as input, in additi…
▽ More
Spurred by the potential of deep learning, computational music generation has gained renewed academic interest. A crucial issue in music generation is that of user control, especially in scenarios where the music generation process is conditioned on existing musical material. Here we propose a model for conditional kick drum track generation that takes existing musical material as input, in addition to a low-dimensional code that encodes the desired relation between the existing material and the new material to be generated. These relational codes are learned in an unsupervised manner from a music dataset. We show that codes can be sampled to create a variety of musically plausible kick drum tracks and that the model can be used to transfer kick drum patterns from one song to another. Lastly, we demonstrate that the learned codes are largely invariant to tempo and time-shift.
△ Less
Submitted 2 August, 2019;
originally announced August 2019.
-
Learning Complex Basis Functions for Invariant Representations of Audio
Authors:
Stefan Lattner,
Monika Dörfler,
Andreas Arzt
Abstract:
Learning features from data has shown to be more successful than using hand-crafted features for many machine learning tasks. In music information retrieval (MIR), features learned from windowed spectrograms are highly variant to transformations like transposition or time-shift. Such variances are undesirable when they are irrelevant for the respective MIR task. We propose an architecture called C…
▽ More
Learning features from data has shown to be more successful than using hand-crafted features for many machine learning tasks. In music information retrieval (MIR), features learned from windowed spectrograms are highly variant to transformations like transposition or time-shift. Such variances are undesirable when they are irrelevant for the respective MIR task. We propose an architecture called Complex Autoencoder (CAE) which learns features invariant to orthogonal transformations. Mapping signals onto complex basis functions learned by the CAE results in a transformation-invariant "magnitude space" and a transformation-variant "phase space". The phase space is useful to infer transformations between data pairs. When exploiting the invariance-property of the magnitude space, we achieve state-of-the-art results in audio-to-score alignment and repeated section discovery for audio. A PyTorch implementation of the CAE, including the repeated section discovery method, is available online.
△ Less
Submitted 12 July, 2019;
originally announced July 2019.
-
Audio-to-Score Alignment using Transposition-invariant Features
Authors:
Andreas Arzt,
Stefan Lattner
Abstract:
Audio-to-score alignment is an important pre-processing step for in-depth analysis of classical music. In this paper, we apply novel transposition-invariant audio features to this task. These low-dimensional features represent local pitch intervals and are learned in an unsupervised fashion by a gated autoencoder. Our results show that the proposed features are indeed fully transposition-invariant…
▽ More
Audio-to-score alignment is an important pre-processing step for in-depth analysis of classical music. In this paper, we apply novel transposition-invariant audio features to this task. These low-dimensional features represent local pitch intervals and are learned in an unsupervised fashion by a gated autoencoder. Our results show that the proposed features are indeed fully transposition-invariant and enable accurate alignments between transposed scores and performances. Furthermore, they can even outperform widely used features for audio-to-score alignment on `untransposed data', and thus are a viable and more flexible alternative to well-established features for music alignment and matching.
△ Less
Submitted 19 July, 2018;
originally announced July 2018.
-
A Predictive Model for Music Based on Learned Interval Representations
Authors:
Stefan Lattner,
Maarten Grachten,
Gerhard Widmer
Abstract:
Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly "absolute pitch perception". Therefore, they fail to generalize over musical concepts which are commonly perceived in terms of relative distances between pitches (e.g., melodies, scale types, modes, cadences, or chord types). Second, they fall short of capturing the con…
▽ More
Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly "absolute pitch perception". Therefore, they fail to generalize over musical concepts which are commonly perceived in terms of relative distances between pitches (e.g., melodies, scale types, modes, cadences, or chord types). Second, they fall short of capturing the concepts of repetition and musical form. In this paper we introduce the recurrent gated autoencoder (RGAE), a recurrent neural network which learns and operates on interval representations of musical sequences. The relative pitch modeling increases generalization and reduces sparsity in the input data. Furthermore, it can learn sequences of copy-and-shift operations (i.e. chromatically transposed copies of musical fragments)---a promising capability for learning musical repetition structure. We show that the RGAE improves the state of the art for general connectionist sequence models in learning to predict monophonic melodies, and that ensembles of relative and absolute music processing models improve the results appreciably. Furthermore, we show that the relative pitch processing of the RGAE naturally facilitates the learning and the generation of sequences of copy-and-shift operations, wherefore the RGAE greatly outperforms a common absolute pitch recurrent neural network on this task.
△ Less
Submitted 22 June, 2018;
originally announced June 2018.
-
Learning Transposition-Invariant Interval Features from Symbolic Music and Audio
Authors:
Stefan Lattner,
Maarten Grachten,
Gerhard Widmer
Abstract:
Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be useful to operate on interval representations rather than on the raw musical surface. Moreover, interval representations are transposition-invariant, valuable fo…
▽ More
Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be useful to operate on interval representations rather than on the raw musical surface. Moreover, interval representations are transposition-invariant, valuable for tasks like audio alignment, cover song detection and music structure analysis. We employ a gated autoencoder to learn fixed-length, invertible and transposition-invariant interval representations from polyphonic music in the symbolic domain and in audio. An unsupervised training method is proposed yielding an organization of intervals in the representation space which is musically plausible. Based on the representations, a transposition-invariant self-similarity matrix is constructed and used to determine repeated sections in symbolic music and in audio, yielding competitive results in the MIREX task "Discovery of Repeated Themes and Sections".
△ Less
Submitted 4 February, 2019; v1 submitted 21 June, 2018;
originally announced June 2018.
-
Learning Musical Relations using Gated Autoencoders
Authors:
Stefan Lattner,
Maarten Grachten,
Gerhard Widmer
Abstract:
Music is usually highly structured and it is still an open question how to design models which can successfully learn to recognize and represent musical structure. A fundamental problem is that structurally related patterns can have very distinct appearances, because the structural relationships are often based on transformations of musical material, like chromatic or diatonic transposition, inver…
▽ More
Music is usually highly structured and it is still an open question how to design models which can successfully learn to recognize and represent musical structure. A fundamental problem is that structurally related patterns can have very distinct appearances, because the structural relationships are often based on transformations of musical material, like chromatic or diatonic transposition, inversion, retrograde, or rhythm change. In this preliminary work, we study the potential of two unsupervised learning techniques - Restricted Boltzmann Machines (RBMs) and Gated Autoencoders (GAEs) - to capture pre-defined transformations from constructed data pairs. We evaluate the models by using the learned representations as inputs in a discriminative task where for a given type of transformation (e.g. diatonic transposition), the specific relation between two musical patterns must be recognized (e.g. an upward transposition of diatonic steps). Furthermore, we measure the reconstruction error of models when reconstructing musical transformed patterns. Lastly, we test the models in an analogy-making task. We find that it is difficult to learn musical transformations with the RBM and that the GAE is much more adequate for this task, since it is able to learn representations of specific transformations that are largely content-invariant. We believe these results show that models such as GAEs may provide the basis for more encompassing music analysis systems, by endowing them with a better understanding of the structures underlying music.
△ Less
Submitted 17 August, 2017;
originally announced August 2017.
-
Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation
Authors:
Stefan Lattner,
Maarten Grachten
Abstract:
Content-invariance in mapping codes learned by GAEs is a useful feature for various relation learning tasks. In this paper we show that the content-invariance of mapping codes for images of 2D and 3D rotated objects can be substantially improved by extending the standard GAE loss (symmetric reconstruction error) with a regularization term that penalizes the symmetric cross-reconstruction error. Th…
▽ More
Content-invariance in mapping codes learned by GAEs is a useful feature for various relation learning tasks. In this paper we show that the content-invariance of mapping codes for images of 2D and 3D rotated objects can be substantially improved by extending the standard GAE loss (symmetric reconstruction error) with a regularization term that penalizes the symmetric cross-reconstruction error. This error term involves reconstruction of pairs with mapping codes obtained from other pairs exhibiting similar transformations. Although this would principally require knowledge of the transformations exhibited by training pairs, our experiments show that a bootstrapping approach can sidestep this issue, and that the regularization term can effectively be used in an unsupervised setting.
△ Less
Submitted 5 July, 2017;
originally announced July 2017.
-
Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
Authors:
Stefan Lattner,
Maarten Grachten,
Gerhard Widmer
Abstract:
We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative model is combined with gradient descent constraint optimisation to provide further control over the generation process. Among other things, this allows for the use of a "template" piece, from which some structural properties can be extracted…
▽ More
We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative model is combined with gradient descent constraint optimisation to provide further control over the generation process. Among other things, this allows for the use of a "template" piece, from which some structural properties can be extracted, and transferred as constraints to the newly generated material. The sampling process is guided with Simulated Annealing to avoid local optima, and to find solutions that both satisfy the constraints, and are relatively stable with respect to the C-RBM. Results show that with this approach it is possible to control the higher-level self-similarity structure, the meter, and the tonal properties of the resulting musical piece, while preserving its local musical coherence.
△ Less
Submitted 14 April, 2018; v1 submitted 14 December, 2016;
originally announced December 2016.