Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–10 of 10 results for author: Chandna, P

Searching in archive cs. Search in all archives.
.
  1. arXiv:2212.13581  [pdf, other

    cs.SD eess.AS

    Voice conversion with limited data and limitless data augmentations

    Authors: Olga Slizovskaia, Jordi Janer, Pritish Chandna, Oscar Mayor

    Abstract: Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this task has gained significant interest where most systems use data-driven machine learning models. Doing the conversion in a low-latency real-world scenario is ev… ▽ More

    Submitted 27 December, 2022; originally announced December 2022.

  2. arXiv:2105.10371  [pdf, other

    cs.SD cs.LG eess.AS

    LoopNet: Musical Loop Synthesis Conditioned On Intuitive Musical Parameters

    Authors: Pritish Chandna, António Ramires, Xavier Serra, Emilia Gómez

    Abstract: Loops, seamlessly repeatable musical segments, are a cornerstone of modern music production. Contemporary artists often mix and match various sampled or pre-recorded loops based on musical criteria such as rhythm, harmony and timbral texture to create compositions. Taking such criteria into account, we present LoopNet, a feed-forward generative model for creating loops conditioned on intuitive par… ▽ More

    Submitted 21 May, 2021; originally announced May 2021.

  3. arXiv:2009.09875  [pdf, other

    eess.AS cs.LG

    A Deep Learning Based Analysis-Synthesis Framework For Unison Singing

    Authors: Pritish Chandna, Helena Cuesta, Emilia Gómez

    Abstract: Unison singing is the name given to an ensemble of singers simultaneously singing the same melody and lyrics. While each individual singer in a unison sings the same principle melody, there are slight timing and pitch deviations between the singers, which, along with the ensemble of timbres, give the listener a perceived sense of "unison". In this paper, we present a study of unison singing in the… ▽ More

    Submitted 21 September, 2020; originally announced September 2020.

  4. arXiv:2008.07645  [pdf, other

    eess.AS cs.LG cs.SD

    Deep Learning Based Source Separation Applied To Choir Ensembles

    Authors: Darius Petermann, Pritish Chandna, Helena Cuesta, Jordi Bonada, Emilia Gomez

    Abstract: Choral singing is a widely practiced form of ensemble singing wherein a group of people sing simultaneously in polyphonic harmony. The most commonly practiced setting for choir ensembles consists of four parts; Soprano, Alto, Tenor and Bass (SATB), each with its own range of fundamental frequencies (F$0$s). The task of source separation for this choral setting entails separating the SATB mixture i… ▽ More

    Submitted 17 August, 2020; originally announced August 2020.

    Comments: To appear at the 21st International Society for Music Information Retrieval Conference, Montréal, Canada, 2020, audio examples available at: "https://darius522.github.io/satb-source-separation-results/"

  5. arXiv:2002.04933  [pdf, other

    eess.AS cs.LG cs.SD

    Content Based Singing Voice Extraction From a Musical Mixture

    Authors: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez

    Abstract: We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder decoder architecture and takes as input the magnitude component of the spectrogram of a musical mixture with vocals. The encoder part of the model is trained via knowledge distillation using a teacher network to learn a… ▽ More

    Submitted 17 February, 2020; v1 submitted 12 February, 2020; originally announced February 2020.

    Comments: To be published in ICASSP 2020

    Journal ref: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain

  6. arXiv:1911.11853  [pdf, other

    eess.AS cs.LG cs.SD stat.ML

    Neural Percussive Synthesis Parameterised by High-Level Timbral Features

    Authors: António Ramires, Pritish Chandna, Xavier Favory, Emilia Gómez, Xavier Serra

    Abstract: We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for intuitive control of a synthesizer, enabling the user to shape sounds without extensive knowledge of signal processing. We use a feedforward convolutional neural network-based architecture, which is able to map input para… ▽ More

    Submitted 3 April, 2020; v1 submitted 25 November, 2019; originally announced November 2019.

  7. arXiv:1904.05086  [pdf, other

    cs.SD cs.LG cs.MM eess.AS

    A Framework for Multi-f0 Modeling in SATB Choir Recordings

    Authors: Helena Cuesta, Emilia Gómez, Pritish Chandna

    Abstract: Fundamental frequency (f0) modeling is an important but relatively unexplored aspect of choir singing. Performance evaluation as well as auditory analysis of singing, whether individually or in a choir, often depend on extracting f0 contours for the singing voice. However, due to the large number of singers, singing at a similar frequency range, extracting the exact individual pitch contours from… ▽ More

    Submitted 10 April, 2019; originally announced April 2019.

  8. WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN

    Authors: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez

    Abstract: We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for acoustic modelling, to separate the influence of pitch and timbre. This facilitates the modelling of the large variability of pitch in the singing voice. Our network… ▽ More

    Submitted 19 June, 2019; v1 submitted 26 March, 2019; originally announced March 2019.

    Journal ref: 2019 27th European Signal Processing Conference (EUSIPCO)

  9. A Vocoder Based Method For Singing Voice Extraction

    Authors: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez

    Abstract: This paper presents a novel method for extracting the vocal track from a musical mixture. The musical mixture consists of a singing voice and a backing track which may comprise of various instruments. We use a convolutional network with skip and residual connections as well as dilated convolutions to estimate vocoder parameters, given the spectrogram of an input mixture. The estimated parameters a… ▽ More

    Submitted 23 April, 2019; v1 submitted 18 March, 2019; originally announced March 2019.

    Journal ref: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

  10. arXiv:1807.03046  [pdf, ps, other

    cs.SD cs.IR cs.LG cs.MM eess.AS stat.ML

    Deep Learning for Singing Processing: Achievements, Challenges and Impact on Singers and Listeners

    Authors: Emilia Gómez, Merlijn Blaauw, Jordi Bonada, Pritish Chandna, Helena Cuesta

    Abstract: This paper summarizes some recent advances on a set of tasks related to the processing of singing using state-of-the-art deep learning techniques. We discuss their achievements in terms of accuracy and sound quality, and the current challenges, such as availability of data and computing resources. We also discuss the impact that these advances do and will have on listeners and singers when they ar… ▽ More

    Submitted 9 July, 2018; originally announced July 2018.

    Comments: Keynote speech, 2018 Joint Workshop on Machine Learning for Music. The Federated Artificial Intelligence Meeting (FAIM), a joint workshop program of ICML, IJCAI/ECAI, and AAMAS

    MSC Class: 97M80