{"id":"https://openalex.org/W4408355557","doi":"https://doi.org/10.1109/icassp49660.2025.10889835","title":"Weak-to-Strong Generalization in Speech Recognition","display_name":"Weak-to-Strong Generalization in Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355557","doi":"https://doi.org/10.1109/icassp49660.2025.10889835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,United States","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,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["Google,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"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":"Kartik Audhkhasi","raw_affiliation_strings":["Google,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","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":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,United States","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9829000234603882,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9829000234603882,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9465000033378601,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9217000007629395,"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/speech-recognition","display_name":"Speech recognition","score":0.7281049489974976},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6583694219589233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503638029098511},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3482993543148041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34032243490219116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17079374194145203}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7281049489974976},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6583694219589233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503638029098511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3482993543148041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34032243490219116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17079374194145203},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2508418541","https://openalex.org/W2797303992","https://openalex.org/W2911038074","https://openalex.org/W2964245029","https://openalex.org/W3008181812","https://openalex.org/W3016010032","https://openalex.org/W3016234571","https://openalex.org/W3026041220","https://openalex.org/W3035160371","https://openalex.org/W3046667470","https://openalex.org/W3097777922","https://openalex.org/W4224919704","https://openalex.org/W4225529283","https://openalex.org/W4319862663","https://openalex.org/W4372260363","https://openalex.org/W4375869286","https://openalex.org/W4392904087","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6850218400","https://openalex.org/W6859347769","https://openalex.org/W6860041859","https://openalex.org/W6861930953","https://openalex.org/W6868951638","https://openalex.org/W6869280431"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W3162204513","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3204019825"],"abstract_inverted_index":{"To":[0,15],"surpass":[1],"human-level":[2],"accuracy,":[3],"speech":[4,70,124],"recognition":[5],"models":[6,22,45],"must":[7,19],"go":[8],"beyond":[9],"relying":[10],"solely":[11],"on":[12,127],"human":[13],"labels.":[14,55],"this":[16,27,57],"end,":[17],"we":[18,59,145],"build":[20],"stronger":[21],"from":[23,74,81,102,135,141],"weaker":[24],"supervisors":[25],"and":[26,78,93,138],"is":[28],"the":[29,75,142,148,158],"main":[30],"goal":[31],"in":[32,116],"weak-to-strong":[33],"generalization":[34],"(WSG).":[35],"WSG":[36,68],"methods":[37],"normally":[38],"incorporate":[39],"additional":[40,64],"information":[41,65],"into":[42],"weak":[43],"teacher":[44],"to":[46,66,121],"improve":[47],"their":[48],"performance":[49],"for":[50,69,105,157],"example":[51],"reliability":[52],"of":[53,63],"teacher-generated":[54],"In":[56],"research,":[58],"investigate":[60],"two":[61],"sources":[62],"implement":[67],"recognition:":[71],"unsupervised":[72,89,139],"data":[73,80,90,101,134,140],"target":[76,143],"language":[77],"supervised":[79,100,133],"other":[82],"similar":[83,103,136],"languages.":[84,129],"We":[85],"study":[86],"scenarios":[87],"where":[88],"boosts":[91],"performance,":[92],"propose":[94],"a":[95,122,162],"new":[96],"clustering":[97,109],"method":[98,110],"leveraging":[99],"languages":[104,137,160],"further":[106,146],"gains.":[107],"Our":[108],"yields":[111],"an":[112],"average":[113],"8%":[114],"reduction":[115],"word":[117],"error":[118],"rate":[119],"compared":[120],"universal":[123],"model":[125,150],"trained":[126],"182":[128],"By":[130],"incorporating":[131],"both":[132],"language,":[144],"enhance":[147],"USM":[149],"by":[151],"10%.":[152],"This":[153],"improvement":[154],"reaches":[155],"15%":[156],"top-performing":[159],"with":[161],"WER":[163],"below":[164],"50%.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}