{"id":"https://openalex.org/W2935711438","doi":"https://doi.org/10.1109/icassp.2019.8683277","title":"Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder","display_name":"Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2935711438","doi":"https://doi.org/10.1109/icassp.2019.8683277","mag":"2935711438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.06464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028298718","display_name":"Cristina G\u00e2rbacea","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cristina G\u00e2rbacea","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039776447","display_name":"A\u00e4ron van den Oord","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A\u00e4ron van den Oord","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102705813","display_name":"Yazhe Li","orcid":"https://orcid.org/0000-0002-8294-7630"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yazhe Li","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008147916","display_name":"Felicia S. C. Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felicia S C Lim","raw_affiliation_strings":["Google, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Google, San Francisco, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030815835","display_name":"Alejandro Luebs","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Luebs","raw_affiliation_strings":["Google, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Google, San Francisco, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oriol Vinyals","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003608440","display_name":"Thomas C. Walters","orcid":"https://orcid.org/0000-0003-1623-9238"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas C Walters","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028298718"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":5.5176,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.966722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"735","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9994000196456909,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7530678510665894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7050834894180298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6991212368011475},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.6889960765838623},{"id":"https://openalex.org/keywords/harmonic-vector-excitation-coding","display_name":"Harmonic Vector Excitation Coding","score":0.6701486110687256},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.5793736577033997},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5609538555145264},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.520982563495636},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5151152014732361},{"id":"https://openalex.org/keywords/vector-sum-excited-linear-prediction","display_name":"Vector sum excited linear prediction","score":0.48551082611083984},{"id":"https://openalex.org/keywords/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.4730070233345032},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.41642695665359497},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3412567973136902},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3369978964328766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1733931601047516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1619587540626526},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1365179419517517}],"concepts":[{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7530678510665894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7050834894180298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991212368011475},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.6889960765838623},{"id":"https://openalex.org/C80167644","wikidata":"https://www.wikidata.org/wiki/Q463990","display_name":"Harmonic Vector Excitation Coding","level":3,"score":0.6701486110687256},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.5793736577033997},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5609538555145264},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.520982563495636},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5151152014732361},{"id":"https://openalex.org/C138807605","wikidata":"https://www.wikidata.org/wiki/Q7917845","display_name":"Vector sum excited linear prediction","level":5,"score":0.48551082611083984},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.4730070233345032},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.41642695665359497},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3412567973136902},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3369978964328766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1733931601047516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1619587540626526},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1365179419517517},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.06464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.06464","pdf_url":"https://arxiv.org/pdf/1910.06464","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.06464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.06464","pdf_url":"https://arxiv.org/pdf/1910.06464","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1959608418","https://openalex.org/W2108532241","https://openalex.org/W2165291881","https://openalex.org/W2292235217","https://openalex.org/W2309400744","https://openalex.org/W2519091744","https://openalex.org/W2552465432","https://openalex.org/W2604231067","https://openalex.org/W2616159609","https://openalex.org/W2632564668","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2808706139","https://openalex.org/W2892620417","https://openalex.org/W2950237263","https://openalex.org/W2951004968","https://openalex.org/W2962676454","https://openalex.org/W2963182577","https://openalex.org/W2963449488","https://openalex.org/W2963799213","https://openalex.org/W3124456579","https://openalex.org/W4294567867","https://openalex.org/W6640963894","https://openalex.org/W6696768431","https://openalex.org/W6734035190","https://openalex.org/W6735849998","https://openalex.org/W6738494155","https://openalex.org/W6752888775","https://openalex.org/W6755135894"],"related_works":["https://openalex.org/W1551277881","https://openalex.org/W2135636570","https://openalex.org/W1546003327","https://openalex.org/W568589707","https://openalex.org/W1544698548","https://openalex.org/W1922590510","https://openalex.org/W60220233","https://openalex.org/W2015120690","https://openalex.org/W2127932871","https://openalex.org/W2766337133"],"abstract_inverted_index":{"In":[0,33,99],"order":[1],"to":[2,53,129],"efficiently":[3],"transmit":[4],"and":[5,66,93],"store":[6],"speech":[7,9,58,106,119],"signals,":[8],"codecs":[10],"create":[11],"a":[12,39,47,116],"minimally":[13],"redundant":[14],"representation":[15],"of":[16,125],"the":[17,25,28,71,87,108,113],"input":[18],"signal":[19],"which":[20,82],"is":[21,83],"then":[22],"decoded":[23],"at":[24,76,90,96,120,134],"receiver":[26],"with":[27,46,60,107],"best":[29],"possible":[30],"perceptual":[31,80,127],"quality.":[32,63],"this":[34],"work":[35],"we":[36],"demonstrate":[37],"that":[38,130],"neural":[40],"network":[41],"architecture":[42],"based":[43],"on":[44,70,103],"VQ-VAE":[45],"WaveNet":[48],"decoder":[49],"can":[50],"be":[51],"used":[52],"perform":[54],"very":[55],"low":[56],"bit-rate":[57],"coding":[59,74,118],"high":[61],"reconstruction":[62],"A":[64],"prosody-transparent":[65],"speaker-independent":[67],"model":[68,117],"trained":[69],"LibriSpeech":[72],"corpus":[73],"audio":[75],"1.6":[77,121],"kbps":[78,92,122],"exhibits":[79],"quality":[81,128],"around":[84],"halfway":[85],"between":[86],"MELP":[88],"codec":[89,95],"2.4":[91],"AMR-WB":[94,133],"23.05":[97,135],"kbps.":[98,136],"addition,":[100],"when":[101],"training":[102,114],"high-quality":[104],"recorded":[105],"test":[109],"speaker":[110],"included":[111],"in":[112],"set,":[115],"produces":[123],"output":[124],"similar":[126],"generated":[131],"by":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}