{"id":"https://openalex.org/W3100270690","doi":"https://doi.org/10.1109/taslp.2019.2938863","title":"Unsupervised Speech Representation Learning Using WaveNet Autoencoders","display_name":"Unsupervised Speech Representation Learning Using WaveNet Autoencoders","publication_year":2019,"publication_date":"2019-09-03","ids":{"openalex":"https://openalex.org/W3100270690","doi":"https://doi.org/10.1109/taslp.2019.2938863","mag":"3100270690"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2938863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2938863","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.08810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I219388962","display_name":"University of Wroc\u0142aw","ror":"https://ror.org/00yae6e25","country_code":"PL","type":"education","lineage":["https://openalex.org/I219388962"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["Institute of Computer Science, University of Wroc\u0142aw, Wroc\u0142aw, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Wroc\u0142aw, Wroc\u0142aw, Poland","institution_ids":["https://openalex.org/I219388962","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Samy Bengio","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":"Samy Bengio","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aaron van den Oord","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google 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":"Aaron van den Oord","raw_affiliation_strings":["DeepMind Technologies, London, U.K"],"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, U.K","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219388962","https://openalex.org/I4210087266"],"apc_list":null,"apc_paid":null,"fwci":19.9385,"has_fulltext":false,"cited_by_count":206,"citation_normalized_percentile":{"value":0.99455818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"12","first_page":"2041","last_page":"2053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8907999992370605,"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":0.8907999992370605,"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":0.05990000069141388,"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/T11448","display_name":"Face recognition and analysis","score":0.004399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.84579998254776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.517300009727478},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48559999465942383},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.48399999737739563},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4715000092983246},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.461899995803833},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.42809998989105225},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41679999232292175},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.3950999975204468}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.84579998254776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115999817848206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5185999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3950999975204468},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2019.2938863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2938863","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1901.08810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.08810","pdf_url":"https://arxiv.org/pdf/1901.08810","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:1901.08810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.08810","pdf_url":"https://arxiv.org/pdf/1901.08810","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1498436455","https://openalex.org/W1840435438","https://openalex.org/W1849277567","https://openalex.org/W1902027874","https://openalex.org/W1970890968","https://openalex.org/W1993660824","https://openalex.org/W2025768430","https://openalex.org/W2057007397","https://openalex.org/W2059652044","https://openalex.org/W2061883090","https://openalex.org/W2086161653","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2100495367","https://openalex.org/W2108598243","https://openalex.org/W2114347655","https://openalex.org/W2120209245","https://openalex.org/W2132037657","https://openalex.org/W2143612262","https://openalex.org/W2145889472","https://openalex.org/W2146444479","https://openalex.org/W2180849752","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2408093180","https://openalex.org/W2468716020","https://openalex.org/W2618530766","https://openalex.org/W2740747242","https://openalex.org/W2750248772","https://openalex.org/W2752796333","https://openalex.org/W2785415724","https://openalex.org/W2786902352","https://openalex.org/W2787223168","https://openalex.org/W2888911345","https://openalex.org/W2962824709","https://openalex.org/W2963223306","https://openalex.org/W2963425185","https://openalex.org/W2963620343","https://openalex.org/W2963804033","https://openalex.org/W2963918774","https://openalex.org/W2964243274","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6637061625","https://openalex.org/W6637618735","https://openalex.org/W6640963894","https://openalex.org/W6675022971","https://openalex.org/W6678292227","https://openalex.org/W6679434410","https://openalex.org/W6679718588","https://openalex.org/W6682132143","https://openalex.org/W6690026940","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6712560600","https://openalex.org/W6713745070","https://openalex.org/W6714142977","https://openalex.org/W6727690538","https://openalex.org/W6729906282","https://openalex.org/W6731370813","https://openalex.org/W6731535438","https://openalex.org/W6733471323","https://openalex.org/W6734194636","https://openalex.org/W6736723571","https://openalex.org/W6742080785","https://openalex.org/W6742082877","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6745388339","https://openalex.org/W6749825310","https://openalex.org/W6751097180","https://openalex.org/W6751433836","https://openalex.org/W6755300632","https://openalex.org/W6755490972","https://openalex.org/W6761568071","https://openalex.org/W6764882207","https://openalex.org/W6857890821"],"related_works":[],"abstract_inverted_index":{"We":[0,110,131,175],"consider":[1],"the":[2,36,50,54,62,86,92,99,107,133,143,150,164,168,182,187,191,198,202],"task":[3],"of":[4,7,11,94,101,135,140,170,190],"unsupervised":[5,205],"extraction":[6],"meaningful":[8],"latent":[9,108],"representations":[10,137,183],"speech":[12,19],"by":[13,85],"applying":[14],"autoencoding":[15],"neural":[16],"networks":[17],"to":[18,24,29,44,67,74,81,106,145,152,173,184],"waveforms.":[20],"The":[21],"goal":[22],"is":[23,65,104],"learn":[25],"a":[26,76,114,119,125,177],"representation":[27,64],"able":[28],"capture":[30],"high":[31,77],"level":[32,47],"semantic":[33],"content":[34,189],"from":[35,88],"signal,":[37],"e.g.":[38],"phoneme":[39],"identities,":[40],"while":[41],"being":[42],"invariant":[43],"confounding":[45],"low":[46],"details":[48],"in":[49,138,201],"signal":[51],"such":[52],"as":[53],"underlying":[55],"pitch":[56],"contour":[57],"or":[58],"background":[59],"noise.":[60],"Since":[61],"learned":[63,136],"tuned":[66],"contain":[68],"only":[69],"phonetic":[70,147,188],"content,":[71,148],"we":[72,166],"resort":[73],"using":[75,163],"capacity":[78],"WaveNet":[79],"decoder":[80],"infer":[82],"information":[83],"discarded":[84],"encoder":[87],"previous":[89],"samples.":[90],"Moreover,":[91,158],"behavior":[93],"autoencoder":[95],"models":[96],"depends":[97],"on":[98,186],"kind":[100],"constraint":[102],"that":[103,180],"applied":[105],"representation.":[109],"compare":[111],"three":[112],"variants:":[113],"simple":[115],"dimensionality":[116],"reduction":[117],"bottleneck,":[118],"Gaussian":[120],"Variational":[121],"Autoencoder":[122],"(VAE),":[123],"and":[124,149,193],"discrete":[126,160],"Vector":[127],"Quantized":[128],"VAE":[129],"(VQ-VAE).":[130],"analyze":[132],"quality":[134],"terms":[139],"speaker":[141],"independence,":[142],"ability":[144,151],"predict":[146],"accurately":[153],"reconstruct":[154],"individual":[155],"spectrogram":[156],"frames.":[157],"for":[159],"encodings":[161],"extracted":[162],"VQ-VAE,":[165],"measure":[167],"ease":[169],"mapping":[171],"them":[172],"phonemes.":[174],"introduce":[176],"regularization":[178],"scheme":[179],"forces":[181],"focus":[185],"utterance":[192],"report":[194],"performance":[195],"comparable":[196],"with":[197],"top":[199],"entries":[200],"ZeroSpeech":[203],"2017":[204],"acoustic":[206],"unit":[207],"discovery":[208],"task.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":64},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2020-11-23T00:00:00"}