{"id":"https://openalex.org/W4210690962","doi":"https://doi.org/10.1109/asru51503.2021.9688018","title":"Injecting Text in Self-Supervised Speech Pretraining","display_name":"Injecting Text in Self-Supervised Speech Pretraining","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210690962","doi":"https://doi.org/10.1109/asru51503.2021.9688018"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688018","doi":"https://doi.org/10.1109/asru51503.2021.9688018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688018","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.12226","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340","observed_orcids":["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":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833","observed_orcids":["https://orcid.org/0000-0002-9505-1833","https://orcid.org/0000-0003-4808-5560","https://orcid.org/0000-0002-2842-6340"]},"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/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390","observed_orcids":["https://orcid.org/0000-0003-1780-4390"]},"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":"Andrew Rosenberg","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/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":"https://orcid.org/0000-0002-8049-2345","observed_orcids":["https://orcid.org/0000-0002-8049-2345"]},"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":"Bhuvana Ramabhadran","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/A5025935520","display_name":"Gary Wang","orcid":"https://orcid.org/0000-0003-0758-8540","observed_orcids":["https://orcid.org/0000-0003-0758-8540"]},"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":"Gary Wang","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/A5103874391","display_name":"Pedro J. Moreno","orcid":null,"observed_orcids":[]},"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":"Pedro Moreno","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":2.863,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92949326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"258"},"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":9.999999747378752e-05,"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/T10028","display_name":"Topic Modeling","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.5709999799728394},{"id":"https://openalex.org/keywords/synthetic-speech","display_name":"synthetic speech","score":0.6779999732971191},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9259999990463257},{"id":"https://openalex.org/keywords/lexical-representation","display_name":"lexical representation","score":0.5950000286102295},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.7570000290870667},{"id":"https://openalex.org/keywords/librispeech","display_name":"LibriSpeech","score":0.9070000052452087},{"id":"https://openalex.org/keywords/voice-search","display_name":"voice search","score":0.9539999961853027},{"id":"https://openalex.org/keywords/word-error-rate-reduction","display_name":"word error rate reduction","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673903703689575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7227557897567749},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6217463612556458},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.619447648525238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6155163049697876},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5754421353340149},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4864601790904999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447012335062027},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43757423758506775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14693918824195862},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru51503.2021.9688018","doi":"https://doi.org/10.1109/asru51503.2021.9688018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688018","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.12226","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.12226","pdf_url":"https://arxiv.org/pdf/2108.12226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2108.12226","doi":"https://doi.org/10.48550/arxiv.2108.12226","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.12226","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.12226","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.12226","pdf_url":"https://arxiv.org/pdf/2108.12226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210690962.pdf","grobid_xml":"https://content.openalex.org/works/W4210690962.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2117278770","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2526425061","https://openalex.org/W2546938941","https://openalex.org/W2626778328","https://openalex.org/W2747467128","https://openalex.org/W2748679025","https://openalex.org/W2797328513","https://openalex.org/W2808706139","https://openalex.org/W2883586237","https://openalex.org/W2885185669","https://openalex.org/W2897548994","https://openalex.org/W2898727538","https://openalex.org/W2899391631","https://openalex.org/W2936774411","https://openalex.org/W2938947737","https://openalex.org/W2939111082","https://openalex.org/W2943008652","https://openalex.org/W2945078028","https://openalex.org/W2962699523","https://openalex.org/W2962911098","https://openalex.org/W2963432880","https://openalex.org/W2963739817","https://openalex.org/W2963796886","https://openalex.org/W2972359262","https://openalex.org/W2972970915","https://openalex.org/W2975100556","https://openalex.org/W2991951200","https://openalex.org/W2995181338","https://openalex.org/W3001197829","https://openalex.org/W3007073761","https://openalex.org/W3011956499","https://openalex.org/W3015280134","https://openalex.org/W3016011332","https://openalex.org/W3026041220","https://openalex.org/W3035160371","https://openalex.org/W3036601975","https://openalex.org/W3036878841","https://openalex.org/W3081494755","https://openalex.org/W3084783920","https://openalex.org/W3093579165","https://openalex.org/W3094637009","https://openalex.org/W3095727342","https://openalex.org/W3096273170","https://openalex.org/W3096587983","https://openalex.org/W3097777922","https://openalex.org/W3097890746","https://openalex.org/W3099782249","https://openalex.org/W3139918052","https://openalex.org/W3144173820","https://openalex.org/W3161606033","https://openalex.org/W3169320628","https://openalex.org/W3198442913","https://openalex.org/W3198608154","https://openalex.org/W3198840231","https://openalex.org/W6729383884","https://openalex.org/W6780218876","https://openalex.org/W6782040703","https://openalex.org/W6800705428"],"related_works":["https://openalex.org/W4225272718","https://openalex.org/W4310271076","https://openalex.org/W4372260307","https://openalex.org/W3163605596","https://openalex.org/W3207925072","https://openalex.org/W4297399268","https://openalex.org/W4372347505","https://openalex.org/W4320558443","https://openalex.org/W4285203343","https://openalex.org/W2938947737"],"abstract_inverted_index":{"Self-supervised":[0],"pretraining":[1,23,85,171],"for":[2,120],"Automated":[3],"Speech":[4],"Recognition":[5],"(ASR)":[6],"has":[7],"shown":[8],"varied":[9],"degrees":[10],"of":[11,38,93,123,130,133,140,154],"success.":[12],"In":[13],"this":[14,83],"paper,":[15],"we":[16,150],"propose":[17],"to":[18,118,156,174],"jointly":[19],"learn":[20],"representations":[21,45],"during":[22,78],"from":[24,47,52],"two":[25],"different":[26],"modalities:":[27],"speech":[28,54,62,135,142],"and":[29,55],"text.":[30,57],"The":[31,109],"proposed":[32,110],"method,":[33],"tts4pretrain":[34],"complements":[35],"the":[36,61,97,121,128,144],"power":[37],"contrastive":[39,76],"learning":[40,51,59],"in":[41,60,184,189],"self-supervision":[42],"with":[43,75,106,136,176],"linguistic/lexical":[44],"derived":[46],"synthesized":[48],"speech,":[49,125],"effectively":[50,126],"untranscribed":[53],"unspoken":[56],"Lexical":[58],"encoder":[63,170],"is":[64,73,172],"enforced":[65],"through":[66],"an":[67,115,159],"additional":[68,185],"sequence":[69],"loss":[70,77],"term":[71],"that":[72,82],"coupled":[74],"pretraining.":[79,166],"We":[80],"demonstrate":[81,151],"novel":[84],"method":[86,111],"yields":[87],"Word":[88],"Error":[89],"Rate":[90],"(WER)":[91],"reductions":[92,153],"10%":[94],"relative":[95,187],"on":[96,143,158],"well-benchmarked,":[98],"Librispeech":[99],"task":[100,163],"over":[101,164],"a":[102,177],"state-of-the-art":[103],"baseline":[104],"pretrained":[105],"wav2vec2.0":[107],"only.":[108],"also":[112],"serves":[113],"as":[114],"effective":[116],"strategy":[117],"compensate":[119],"lack":[122],"transcribed":[124,134,141],"matching":[127],"performance":[129],"5000":[131],"hours":[132,139],"just":[137],"100":[138],"AMI":[145],"meeting":[146],"transcription":[147],"task.":[148],"Finally,":[149],"WER":[152],"up":[155],"15%":[157],"inhouse":[160],"Voice":[161],"Search":[162],"traditional":[165],"Incorporating":[167],"text":[168],"into":[169],"complimentary":[173],"rescoring":[175],"larger":[178],"or":[179],"in-domain":[180],"language":[181],"model,":[182],"resulting":[183],"6%":[186],"reduction":[188],"WER.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2022-02-08T00:00:00"}