{"id":"https://openalex.org/W4297841894","doi":"https://doi.org/10.21437/interspeech.2022-399","title":"Unsupervised Data Selection via Discrete Speech Representation for ASR","display_name":"Unsupervised Data Selection via Discrete Speech Representation for ASR","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841894","doi":"https://doi.org/10.21437/interspeech.2022-399"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-399","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039693533","display_name":"Zhiyun Lu","orcid":"https://orcid.org/0000-0002-1733-4061"},"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":"Zhiyun Lu","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"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":"Yongqiang Wang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"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":"Yu Zhang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107931312","display_name":"Wei Han","orcid":"https://orcid.org/0000-0003-0809-5465"},"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":"Wei Han","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"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":"Zhehuai Chen","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3393","last_page":"3397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9961000084877014,"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":0.7660641670227051},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6732640266418457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5773117542266846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522213578224182},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5425127744674683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4948076605796814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33054864406585693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660641670227051},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6732640266418457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5773117542266846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522213578224182},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5425127744674683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4948076605796814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33054864406585693},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-399","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1588359339","https://openalex.org/W1905522558","https://openalex.org/W2062164080","https://openalex.org/W2117278770","https://openalex.org/W2121879602","https://openalex.org/W2141440284","https://openalex.org/W2143577772","https://openalex.org/W2171761326","https://openalex.org/W2513345070","https://openalex.org/W2547875792","https://openalex.org/W2748795451","https://openalex.org/W2797259383","https://openalex.org/W2963366389","https://openalex.org/W2963799213","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W3015419784","https://openalex.org/W3020336359","https://openalex.org/W3026041220","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3102342027","https://openalex.org/W3125709657","https://openalex.org/W3139918052","https://openalex.org/W3160628828","https://openalex.org/W3169320628","https://openalex.org/W3198270883","https://openalex.org/W3198771897","https://openalex.org/W3204696009","https://openalex.org/W4210463634","https://openalex.org/W4210690962","https://openalex.org/W4221161761","https://openalex.org/W4226033575","https://openalex.org/W4285192675","https://openalex.org/W4296069324","https://openalex.org/W4297808394","https://openalex.org/W4307023467","https://openalex.org/W4307106469","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W2383516975"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,54],"of":[2,81,95,97],"speech":[3,12,40,48],"representations":[4],"has":[5],"achieved":[6],"impressive":[7],"results":[8,102,147],"in":[9,51,103,107],"improving":[10],"automatic":[11],"recognition":[13],"(ASR).In":[14],"this":[15],"paper,":[16],"we":[17,72],"show":[18,73],"that":[19,74],"data":[20,33,62,84,100,127],"selection":[21,34,63],"is":[22],"important":[23],"for":[24,128],"self-supervised":[25,53],"learning.We":[26],"propose":[27],"a":[28,42,60,92],"simple":[29],"and":[30,58,85,121,144],"effective":[31],"unsupervised":[32],"method":[35,64,77],"which":[36],"selects":[37],"acoustically":[38],"similar":[39],"to":[41,111,140,149],"target":[43],"domain.It":[44],"takes":[45],"the":[46,66,79,87,98,114,141],"discrete":[47,67],"representation":[49],"available":[50],"common":[52],"frameworks":[55],"as":[56],"input,":[57],"applies":[59],"contrastive":[61],"on":[65,91,113],"tokens.Through":[68],"extensive":[69],"empirical":[70],"studies":[71],"our":[75],"proposed":[76],"reduces":[78,130],"amount":[80],"required":[82],"pre-training":[83,112,129],"improves":[86],"downstream":[88],"ASR":[89],"performance.Pre-training":[90],"selected":[93],"subset":[94],"6%":[96,126],"general":[99],"pool":[101],"11.8%":[104],"relative":[105],"improvements":[106],"LibriSpeech":[108,118],"test-other":[109],"compared":[110,139,148],"full":[115,142],"set.On":[116],"Multilingual":[117],"French,":[119],"German,":[120],"Spanish":[122],"test":[123],"sets,":[124],"selecting":[125],"word":[131],"error":[132],"rate":[133],"by":[134],"more":[135],"than":[136],"15%":[137],"relatively":[138],"set,":[143],"achieves":[145],"competitive":[146],"current":[150],"state-of-theart":[151],"performances.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}