{"id":"https://openalex.org/W4387559820","doi":"https://doi.org/10.48550/arxiv.2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","display_name":"Generative Spoken Language Model based on continuous word-sized audio tokens","publication_year":2023,"publication_date":"2023-10-08","ids":{"openalex":"https://openalex.org/W4387559820","doi":"https://doi.org/10.48550/arxiv.2310.05224"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.05224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05224","pdf_url":"https://arxiv.org/pdf/2310.05224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.05224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071809848","display_name":"Robin Algayres","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Algayres, Robin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adi, Yossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091817823","display_name":"Tu Anh Nguyen","orcid":"https://orcid.org/0000-0002-9623-042X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Tu Anh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020182193","display_name":"Jade Copet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Copet, Jade","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Synnaeve, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077663332","display_name":"Beno\u00eet Sagot","orcid":"https://orcid.org/0000-0002-0107-8526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sagot, Benoit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dupoux, Emmanuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.805853545665741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6120526790618896},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5893535614013672},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5691128373146057},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.565141499042511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5444433093070984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180437564849854},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4627397656440735},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4550716280937195},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4506146013736725},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4505298435688019},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23040884733200073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805853545665741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6120526790618896},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5893535614013672},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5691128373146057},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.565141499042511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5444433093070984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180437564849854},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4627397656440735},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4550716280937195},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4506146013736725},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4505298435688019},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23040884733200073},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2310.05224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05224","pdf_url":"https://arxiv.org/pdf/2310.05224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04402373v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04402373","pdf_url":"https://inria.hal.science/hal-04402373v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023, Singapore, Singapore","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2310.05224","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05224","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.05224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05224","pdf_url":"https://arxiv.org/pdf/2310.05224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387559820.pdf","grobid_xml":"https://content.openalex.org/works/W4387559820.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"In":[0,143],"NLP,":[1],"text":[2],"language":[3,63,101],"models":[4],"based":[5,51,103],"on":[6,52,104,111],"words":[7],"or":[8,30],"subwords":[9],"are":[10,28,153],"known":[11],"to":[12,138],"outperform":[13],"their":[14],"character-based":[15],"counterparts.":[16],"Yet,":[17],"in":[18],"the":[19,22,80,98,145,150],"speech":[20],"community,":[21],"standard":[23],"input":[24],"of":[25],"spoken":[26],"LMs":[27],"20ms":[29],"40ms-long":[31],"discrete":[32,114],"units":[33],"(shorter":[34],"than":[35],"a":[36,45,76,85],"phoneme).":[37],"Taking":[38],"inspiration":[39],"from":[40],"word-based":[41],"LM,":[42],"we":[43],"introduce":[44],"Generative":[46],"Spoken":[47],"Language":[48],"Model":[49],"(GSLM)":[50],"word-size":[53,105],"continuous-valued":[54],"audio":[55],"embeddings":[56,146],"that":[57],"can":[58],"generate":[59],"diverse":[60],"and":[61,88,125,148,155],"expressive":[62],"output.":[64],"This":[65],"is":[66,97,110,131],"obtained":[67],"by":[68,84,91,122],"replacing":[69],"lookup":[70],"table":[71],"for":[72],"lexical":[73],"types":[74],"with":[75,113],"Lexical":[77,151],"Embedding":[78],"function,":[79],"cross":[81],"entropy":[82],"loss":[83],"contrastive":[86],"loss,":[87],"multinomial":[89],"sampling":[90],"k-NN":[92],"sampling.":[93],"The":[94],"resulting":[95],"model":[96,102],"first":[99],"generative":[100],"continuous":[106],"embeddings.":[107],"Its":[108],"performance":[109],"par":[112],"unit":[115],"GSLMs":[116],"regarding":[117],"generation":[118],"quality":[119],"as":[120],"measured":[121],"automatic":[123],"metrics":[124],"subjective":[126],"human":[127],"judgements.":[128],"Moreover,":[129],"it":[130],"five":[132],"times":[133],"more":[134],"memory":[135],"efficient":[136],"thanks":[137],"its":[139],"large":[140],"200ms":[141],"units.":[142],"addition,":[144],"before":[147],"after":[149],"Embedder":[152],"phonetically":[154],"semantically":[156],"interpretable.":[157]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}