{"id":"https://openalex.org/W4402112548","doi":"https://doi.org/10.21437/interspeech.2024-2366","title":"Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer","display_name":"Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112548","doi":"https://doi.org/10.21437/interspeech.2024-2366"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2366","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.08325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055632925","display_name":"Avihu Dekel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avihu Dekel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035109881"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75266285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4174","last_page":"4178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.8391412496566772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.67049241065979},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5657826066017151},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5576700568199158},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.449482798576355},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.4402817189693451},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42856571078300476},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.41853445768356323},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41722580790519714},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.26121407747268677},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.10626158118247986},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08974799513816833},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.0758112370967865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391412496566772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.67049241065979},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5657826066017151},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5576700568199158},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.449482798576355},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.4402817189693451},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42856571078300476},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.41853445768356323},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41722580790519714},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.26121407747268677},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.10626158118247986},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08974799513816833},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0758112370967865},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2366","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.08325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.08325","pdf_url":"https://arxiv.org/pdf/2410.08325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.08325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.08325","pdf_url":"https://arxiv.org/pdf/2410.08325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112548.pdf","grobid_xml":"https://content.openalex.org/works/W4402112548.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2017913521","https://openalex.org/W2152250293","https://openalex.org/W2110178950","https://openalex.org/W2150814427","https://openalex.org/W50552483","https://openalex.org/W2113070424","https://openalex.org/W1480343695","https://openalex.org/W2040901912","https://openalex.org/W2135727925","https://openalex.org/W2407986466"],"abstract_inverted_index":{"Discrete":[0],"Audio":[1],"codecs":[2],"(or":[3],"audio":[4,36,57],"tokenizers)":[5],"have":[6],"recently":[7,31],"regained":[8],"interest":[9],"due":[10],"to":[11,19,45],"the":[12],"ability":[13],"of":[14,92],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"learn":[20],"their":[21],"compressed":[22],"acoustic":[23],"representations.":[24],"Various":[25],"publicly":[26,117],"available":[27,118],"trainable":[28],"discrete":[29],"tokenizers":[30],"demonstrated":[32],"impressive":[33],"results":[34],"for":[35],"tokenization,":[37],"yet":[38],"they":[39],"mostly":[40],"require":[41],"high":[42],"token":[43],"rates":[44],"gain":[46],"high-quality":[47],"reconstruction.":[48],"In":[49],"this":[50],"study,":[51],"we":[52],"fine-tuned":[53],"an":[54],"open-source":[55,62],"general":[56],"RVQGAN":[58],"model":[59,77,123],"using":[60],"diverse":[61],"speech":[63,79,104],"data,":[64],"considering":[65],"various":[66],"recording":[67,108],"conditions":[68],"and":[69],"quality":[70],"levels.":[71],"The":[72,99,122],"resulting":[73],"wideband":[74],"(24kHz)":[75],"speech-only":[76],"achieves":[78],"reconstruction,":[80],"which":[81],"is":[82,124],"nearly":[83],"indistinguishable":[84],"from":[85],"PCM":[86],"(pulse-code":[87],"modulation)":[88],"with":[89],"a":[90],"rate":[91],"150-300":[93],"tokens":[94],"per":[95],"second":[96],"(1500-3000":[97],"bps).":[98],"evaluation":[100],"used":[101],"comprehensive":[102],"English":[103],"data":[105],"encompassing":[106],"different":[107],"conditions,":[109],"including":[110],"studio":[111],"settings.":[112],"Speech":[113],"samples":[114],"are":[115],"made":[116],"in":[119,127],"http://ibm.biz/IS24SpeechRVQ":[120],".":[121],"officially":[125],"released":[126],"https://huggingface.co/ibm/DAC.speech.v1.0":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
