{"id":"https://openalex.org/W4283324001","doi":"https://doi.org/10.21437/interspeech.2022-936","title":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training","display_name":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283324001","doi":"https://doi.org/10.21437/interspeech.2022-936"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-936","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-936","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":"article","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/A5101863385","display_name":"Chengyi Wang","orcid":"https://orcid.org/0000-0002-6780-9299"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengyi Wang","raw_affiliation_strings":["Nankai University"],"affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101863385"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":1.2473,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81275587,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9984999895095825,"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":0.9800999760627747,"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":0.6844537258148193},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6163510084152222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5648016333580017},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4295315146446228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40668249130249023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32203251123428345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32160940766334534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844537258148193},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6163510084152222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5648016333580017},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4295315146446228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40668249130249023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32203251123428345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32160940766334534},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-936","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-936","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1877570817","https://openalex.org/W1993660824","https://openalex.org/W2079623482","https://openalex.org/W2150769028","https://openalex.org/W2150907703","https://openalex.org/W2160815625","https://openalex.org/W2514741789","https://openalex.org/W2808631503","https://openalex.org/W2888867175","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2940322076","https://openalex.org/W2953190524","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3008525923","https://openalex.org/W3015522062","https://openalex.org/W3016011332","https://openalex.org/W3026041220","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3096338464","https://openalex.org/W3160525311","https://openalex.org/W3160799772","https://openalex.org/W3197580070","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4221161761","https://openalex.org/W4225741214","https://openalex.org/W4285666836","https://openalex.org/W4288072840","https://openalex.org/W4288089799","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W1530808388","https://openalex.org/W4366179611","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Recently,":[0],"masked":[1],"prediction":[2],"pre-training":[3,48],"has":[4],"seen":[5],"remarkable":[6],"progress":[7],"in":[8,20,98,125],"self-supervised":[9],"learning":[10],"(SSL)":[11],"for":[12],"speech":[13,41,70,95,128],"recognition.It":[14],"usually":[15],"requires":[16],"a":[17,54,126],"codebook":[18,35],"obtained":[19],"an":[21,74],"unsupervised":[22],"way,":[23],"making":[24],"it":[25],"less":[26],"accurate":[27],"and":[28,45,83,109],"difficult":[29],"to":[30,38,58,106,114],"interpret.We":[31],"propose":[32],"two":[33],"supervision-guided":[34],"generation":[36],"approaches":[37],"improve":[39],"automatic":[40],"recognition":[42],"(ASR)":[43],"performance":[44],"also":[46,121],"the":[47,68,81,89],"efficiency,":[49],"either":[50],"through":[51],"decoding":[52],"with":[53,112],"hybrid":[55,82],"ASR":[56],"system":[57],"generate":[59],"phoneme-level":[60],"alignments":[61],"(named":[62,78],"PBERT),":[63],"or":[64],"performing":[65],"clustering":[66],"on":[67,88],"supervised":[69],"features":[71],"extracted":[72],"from":[73],"end-to-end":[75],"CTC":[76,79,84],"model":[77],"clustering).Both":[80],"models":[85,120],"are":[86],"trained":[87],"same":[90],"small":[91],"amount":[92],"of":[93,103],"labeled":[94],"as":[96],"used":[97],"fine-tuning.Experiments":[99],"demonstrate":[100],"significant":[101],"superiority":[102],"our":[104],"methods":[105],"various":[107],"SSL":[108],"self-training":[110],"baselines,":[111],"up":[113],"17.0%":[115],"relative":[116],"WER":[117],"reduction.Our":[118],"pre-trained":[119],"show":[122],"good":[123],"transferability":[124],"non-ASR":[127],"task.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}