{"id":"https://openalex.org/W4225329198","doi":"https://doi.org/10.1109/icassp43922.2022.9746453","title":"Multilingual Second-Pass Rescoring for Automatic Speech Recognition Systems","display_name":"Multilingual Second-Pass Rescoring for Automatic Speech Recognition Systems","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225329198","doi":"https://doi.org/10.1109/icassp43922.2022.9746453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746453","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"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":"Neeraj Gaur","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/A5076026485","display_name":"Tongzhou Chen","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":"Tongzhou 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/A5040131037","display_name":"Ehsan Variani","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":"Ehsan Variani","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/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"]}]},{"author_position":"middle","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 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},"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 J. 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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6407","last_page":"6411"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.8677747249603271},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7116256356239319},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6499486565589905},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6111423969268799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.591051459312439},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5534272789955139},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5216203927993774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4930281341075897},{"id":"https://openalex.org/keywords/first-pass","display_name":"First pass","score":0.4841616749763489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677747249603271},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7116256356239319},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6499486565589905},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6111423969268799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.591051459312439},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5534272789955139},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5216203927993774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4930281341075897},{"id":"https://openalex.org/C2994044699","wikidata":"https://www.wikidata.org/wiki/Q1330121","display_name":"First pass","level":2,"score":0.4841616749763489},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746453","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1915251500","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2100099270","https://openalex.org/W2142697503","https://openalex.org/W2143612262","https://openalex.org/W2292087804","https://openalex.org/W2327501763","https://openalex.org/W2545177271","https://openalex.org/W2548040684","https://openalex.org/W2627092829","https://openalex.org/W2747467128","https://openalex.org/W2752047430","https://openalex.org/W2888779557","https://openalex.org/W2944255943","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2971840980","https://openalex.org/W2973122799","https://openalex.org/W3008434450","https://openalex.org/W3015506840","https://openalex.org/W3015564377","https://openalex.org/W3016010032","https://openalex.org/W3096371065","https://openalex.org/W3097338456","https://openalex.org/W3097777922","https://openalex.org/W3103005696","https://openalex.org/W3156323585","https://openalex.org/W4385245566","https://openalex.org/W6640059789","https://openalex.org/W6681009388","https://openalex.org/W6696449567","https://openalex.org/W6728910023","https://openalex.org/W6729354880","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6743726175"],"related_works":["https://openalex.org/W8738421","https://openalex.org/W1745277","https://openalex.org/W2308727","https://openalex.org/W3939953","https://openalex.org/W1679128","https://openalex.org/W9840409","https://openalex.org/W1226999","https://openalex.org/W14754660","https://openalex.org/W7963366","https://openalex.org/W11920722"],"abstract_inverted_index":{"Second-pass":[0],"rescoring":[1,62,94,110],"is":[2],"a":[3,97,123,128,162],"well":[4],"known":[5],"technique":[6],"to":[7,105,166,170],"improve":[8,190],"the":[9,23,40,89,92,106,109,135,159,167,172,175,191,205,211,215],"performance":[10,173],"of":[11,91,134,150,154,174,202],"Automatic":[12],"Speech":[13],"Recognition":[14],"(ASR)":[15],"systems.":[16],"Neural":[17],"Oracle":[18],"Search":[19],"(NOS),":[20],"which":[21],"selects":[22],"most":[24],"likely":[25],"hypothesis":[26,30],"from":[27,35],"an":[28,54,132],"N-best":[29,44],"list":[31],"by":[32],"integrating":[33],"information":[34,52],"multiple":[36],"sources,":[37],"such":[38],"as":[39],"input":[41],"acoustic":[42],"representations,":[43],"hypotheses,":[45],"additional":[46],"first-pass":[47,65,68,98,107,117,192],"statistics,":[48],"and":[49,101,125,158,208,213],"unpaired":[50],"textual":[51],"through":[53],"external":[55],"language":[56,164],"model,":[57,108],"has":[58],"shown":[59],"success":[60],"in":[61,196,204,210,218],"for":[63,140],"RNN-T":[64],"models.":[66],"Multilingual":[67],"speech":[69],"recognition":[70],"models":[71],"often":[72],"outperform":[73],"their":[74],"monolingual":[75,216],"counterparts":[76,217],"when":[77],"trained":[78],"on":[79,96,147],"related":[80,155],"or":[81],"low-resource":[82,156],"languages.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,126],"investigate":[88],"use":[90],"NOS":[93,177,188],"model":[95,100,111,119,194],"multilingual":[99,118,176,187,193],"show":[102,185],"that":[103,131],"similar":[104],"can":[112,189],"be":[113,138],"made":[114],"multilingual.":[115],"Our":[116,182],"does":[120],"not":[121],"require":[122],"language-id":[124,136],"make":[127],"realistic":[129],"assumption":[130],"estimate":[133],"would":[137],"available":[139],"second-pass":[141],"rescoring.":[142],"We":[143],"conduct":[144],"comprehensive":[145],"experiments":[146],"two":[148],"sets":[149],"languages,":[151,157],"one":[152],"consisting":[153],"other":[160],"with":[161],"high-resource":[163],"added":[165],"first":[168,206],"set":[169],"analyze":[171],"rescorer":[178],"under":[179],"different":[180],"settings.":[181],"experimental":[183],"results":[184],"that,":[186],"resulting":[195],"average":[197],"word":[198],"error":[199],"rate":[200],"reduction":[201],"9.4%":[203],"case,":[207],"8.4%":[209],"second,":[212],"out-performing":[214],"both":[219],"cases.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}