{"id":"https://openalex.org/W4392904194","doi":"https://doi.org/10.1109/icassp48485.2024.10446250","title":"Monte Carlo Self-Training for Speech Recognition","display_name":"Monte Carlo Self-Training for Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904194","doi":"https://doi.org/10.1109/icassp48485.2024.10446250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446250","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"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":true,"raw_author_name":"Anshuman Tripathi","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025206583","display_name":"Soheil Khorram","orcid":"https://orcid.org/0000-0002-2306-3341"},"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":"Soheil Khorram","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"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":"Han Lu","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344655","display_name":"Jaeyoung Kim","orcid":"https://orcid.org/0000-0002-4830-0454"},"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":"Jaeyoung Kim","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603610","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5975-9781"},"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":"Qian Zhang","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","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":"Hasim Sak","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101403998"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02619108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"12802","last_page":"12806"},"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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/monte-carlo-method","display_name":"Monte Carlo method","score":0.7935664057731628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7273977398872375},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.485072523355484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4597802758216858},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4568714201450348},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.45325878262519836},{"id":"https://openalex.org/keywords/monte-carlo-integration","display_name":"Monte Carlo integration","score":0.41880810260772705},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4180840253829956},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.40516507625579834},{"id":"https://openalex.org/keywords/hybrid-monte-carlo","display_name":"Hybrid Monte Carlo","score":0.34255048632621765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32518500089645386},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.27389881014823914},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2273944616317749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16960278153419495},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09681811928749084}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.7935664057731628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273977398872375},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.485072523355484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4597802758216858},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4568714201450348},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.45325878262519836},{"id":"https://openalex.org/C132725507","wikidata":"https://www.wikidata.org/wiki/Q39879","display_name":"Monte Carlo integration","level":5,"score":0.41880810260772705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4180840253829956},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.40516507625579834},{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.34255048632621765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32518500089645386},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.27389881014823914},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2273944616317749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16960278153419495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09681811928749084},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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:10.1109/icassp48485.2024.10446250","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W2936774411","https://openalex.org/W2953070460","https://openalex.org/W2964110616","https://openalex.org/W2973049979","https://openalex.org/W3008174054","https://openalex.org/W3015522062","https://openalex.org/W3016010032","https://openalex.org/W3026041220","https://openalex.org/W3034368386","https://openalex.org/W3035160371","https://openalex.org/W3091002423","https://openalex.org/W3138154797","https://openalex.org/W3162649911","https://openalex.org/W3204696009","https://openalex.org/W4224919704","https://openalex.org/W4225755266","https://openalex.org/W4226033575","https://openalex.org/W4297847008","https://openalex.org/W6638523607","https://openalex.org/W6733814495","https://openalex.org/W6843161697"],"related_works":["https://openalex.org/W3181069468","https://openalex.org/W2980652010","https://openalex.org/W4294677683","https://openalex.org/W4367155567","https://openalex.org/W2272101450","https://openalex.org/W1548972748","https://openalex.org/W4238572999","https://openalex.org/W590971457","https://openalex.org/W2105032794","https://openalex.org/W3016438207"],"abstract_inverted_index":{"Self-training":[0,36,60,83],"in":[1,113,128],"the":[2,8,15,20,96,135],"teacher-student":[3],"framework":[4],"generally":[5],"suffers":[6],"from":[7,14,44],"confirmation":[9],"bias":[10],"problem,":[11],"where":[12,37],"errors":[13],"teacher":[16,46,98,137],"are":[17,40],"propagated":[18],"to":[19,51,64],"student":[21,72],"and":[22,73,90,118],"hence":[23],"get":[24],"amplified":[25],"with":[26],"multiple":[27],"iterations.":[28],"In":[29,75],"this":[30,53],"paper,":[31],"we":[32,78,119],"present":[33],"Monte":[34,58,81],"Carlo":[35,59,82],"pseudo":[38,110],"labels":[39],"generated":[41],"by":[42],"sampling":[43,107],"a":[45,49,114],"distribution,":[47],"as":[48],"way":[50,117],"mitigate":[52],"problem.":[54],"We":[55,102],"show":[56,104,120],"that":[57,80,105,121],"is":[61,91,100,139],"an":[62],"approximation":[63],"minimizing":[65],"label":[66,106,111],"sequence":[67],"level":[68],"cross":[69],"entropy":[70],"between":[71],"teacher.":[74],"our":[76,129],"experiments":[77,132],"find":[79],"always":[84],"outperforms":[85],"beam":[86],"decoder":[87],"based":[88],"self-training":[89],"quite":[92],"robust":[93],"even":[94],"when":[95,134],"initial":[97,136],"WER":[99,138],"high.":[101,141],"also":[103],"allows":[108],"formulating":[109],"confidence":[112,123],"more":[115],"natural":[116],"these":[122],"measures":[124],"give":[125],"further":[126],"improvements":[127],"unsupervised":[130],"adaptation":[131],"especially":[133],"very":[140]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}