{"id":"https://openalex.org/W3039910566","doi":"https://doi.org/10.1109/slt48900.2021.9383605","title":"Data Augmenting Contrastive Learning of Speech Representations in the Time Domain","display_name":"Data Augmenting Contrastive Learning of Speech Representations in the Time Domain","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3039910566","doi":"https://doi.org/10.1109/slt48900.2021.9383605","mag":"3039910566"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.00991","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034757620","display_name":"Eugene Kharitonov","orcid":"https://orcid.org/0000-0002-3984-5647"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Eugene Kharitonov","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060751140","display_name":"Maude Rivi\u00e8re","orcid":"https://orcid.org/0009-0001-6862-3920"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Morgane Riviere","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040376974","display_name":"Pierre-Emmanuel Mazar\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Pierre-Emmanuel Mazare","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053822883","display_name":"Matthijs Douze","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Matthijs Douze","raw_affiliation_strings":["Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR","IL"],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["EHESS, CNRS, INRIA, ENS-PSL University","Facebook AI Research","Facebook"],"affiliations":[{"raw_affiliation_string":"EHESS, CNRS, INRIA, ENS-PSL University","institution_ids":["https://openalex.org/I90669466","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5034757620"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":1.9598,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88187214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.8341799974441528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5589042901992798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.523448646068573},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46685439348220825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44993144273757935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341799974441528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5589042901992798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.523448646068573},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46685439348220825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44993144273757935},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.00991","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00991","pdf_url":"https://arxiv.org/pdf/2007.00991","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"},{"id":"pmh:oai:HAL:hal-03070321v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03070321","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT 2020 - IEEE Spoken Language Technology Workshop, Dec 2020, Shenzhen / Virtual, China","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2007.00991","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.00991","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/z8cc-xt56","is_oa":true,"landing_page_url":"https://doi.org/10.17023/z8cc-xt56","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.00991","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00991","pdf_url":"https://arxiv.org/pdf/2007.00991","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":53,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989674786","https://openalex.org/W2020607164","https://openalex.org/W2055408826","https://openalex.org/W2148349024","https://openalex.org/W2219249508","https://openalex.org/W2346964103","https://openalex.org/W2347098582","https://openalex.org/W2407080277","https://openalex.org/W2509930204","https://openalex.org/W2593779438","https://openalex.org/W2696967604","https://openalex.org/W2787447541","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2930682606","https://openalex.org/W2936774411","https://openalex.org/W2940544976","https://openalex.org/W2963620343","https://openalex.org/W2970971581","https://openalex.org/W2972943112","https://openalex.org/W2973026522","https://openalex.org/W2973049979","https://openalex.org/W2983785920","https://openalex.org/W2990583358","https://openalex.org/W2995181338","https://openalex.org/W3003875258","https://openalex.org/W3005511757","https://openalex.org/W3005680577","https://openalex.org/W3015213852","https://openalex.org/W3015783745","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3093096176","https://openalex.org/W3100270690","https://openalex.org/W3102342027","https://openalex.org/W6675022971","https://openalex.org/W6677620606","https://openalex.org/W6682250724","https://openalex.org/W6686369942","https://openalex.org/W6688816777","https://openalex.org/W6697293080","https://openalex.org/W6713762819","https://openalex.org/W6748342566","https://openalex.org/W6760822226","https://openalex.org/W6761176036","https://openalex.org/W6761553608","https://openalex.org/W6762619590","https://openalex.org/W6766978945","https://openalex.org/W6769455919","https://openalex.org/W6771812881","https://openalex.org/W6774314701","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2151447942","https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W3107474891","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2131420137"],"abstract_inverted_index":{"Contrastive":[0],"Predictive":[1],"Coding":[2],"(CPC),":[3],"based":[4],"on":[5,34,118,121,129],"predicting":[6],"future":[7,64,90],"segments":[8,13,74,91],"of":[9,23,55,100,111,126,185],"speech":[10,24],"from":[11,75,92],"past":[12,62],"is":[14,80],"emerging":[15],"as":[16],"a":[17,42,124,168],"powerful":[18],"algorithm":[19],"for":[20,52],"representation":[21],"learning":[22],"signal.":[25],"However,":[26],"it":[27,87],"still":[28],"under-performs":[29],"compared":[30],"to":[31,72,89,140],"other":[32],"methods":[33],"unsupervised":[35,119],"evaluation":[36],"benchmarks.":[37],"Here,":[38],"we":[39,48,133,160],"intro-duce":[40],"WavAugment,":[41],"time-domain":[43],"data":[44],"augmentation":[45,70],"library":[46],"which":[47,76,93],"adapt":[49],"and":[50,98,116,151],"optimize":[51],"the":[53,73,77,94,101,108,130,145,153,163,174,189],"specificities":[54],"CPC":[56,78],"(raw":[57],"waveform":[58],"input,":[59],"contrastive":[60,102],"loss,":[61],"versus":[63],"structure).":[65],"We":[66],"find":[67],"that":[68,162],"applying":[69,86],"only":[71],"prediction":[79],"performed":[81],"yields":[82],"better":[83],"results":[84],"than":[85],"also":[88],"samples":[95],"(both":[96],"positive":[97],"negative)":[99],"loss":[103],"are":[104],"drawn.":[105],"After":[106],"selecting":[107],"best":[109],"combination":[110,136],"pitch":[112],"modification,":[113],"additive":[114],"noise":[115],"reverberation":[117],"metrics":[120],"LibriSpeech":[122],"(with":[123],"gain":[125],"18-22%":[127],"relative":[128],"ABX":[131],"score),":[132],"apply":[134],"this":[135],"without":[137],"any":[138],"change":[139],"three":[141],"new":[142],"datasets":[143],"in":[144,173],"Zero":[146],"Resource":[147],"Speech":[148],"Benchmark":[149],"2017":[150],"beat":[152],"state-of-the-art":[154],"using":[155],"out-of-domain":[156],"training":[157],"data.":[158],"Finally,":[159],"show":[161],"data-augmented":[164],"pretrained":[165],"features":[166],"improve":[167],"downstream":[169],"phone":[170],"recognition":[171],"task":[172],"Libri-light":[175],"semi-supervised":[176],"setting":[177],"(10":[178],"min,":[179],"1":[180],"h":[181,184],"or":[182],"10":[183],"labelled":[186],"data)":[187],"reducing":[188],"PER":[190],"by":[191],"15%":[192],"relative.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-07-25T00:00:00"}