{"id":"https://openalex.org/W4372269772","doi":"https://doi.org/10.1109/icassp49357.2023.10096429","title":"Large-Scale Language Model Rescoring on Long-Form Data","display_name":"Large-Scale Language Model Rescoring on Long-Form Data","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269772","doi":"https://doi.org/10.1109/icassp49357.2023.10096429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030888546","display_name":"Cyril Allauzen","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":"Cyril Allauzen","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"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":"Yinghui Huang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613715","display_name":"Daniel Park","orcid":"https://orcid.org/0000-0002-1919-0460"},"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":"Daniel Park","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","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":"David Rybach","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399361","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0002-4817-8858"},"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":"W. Ronny Huang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010848698","display_name":"Rodrigo Cabrera","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":"Rodrigo Cabrera","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X"},"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":"Michael Riley","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","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":15,"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/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":0.9994999766349792,"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":0.9991000294685364,"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":0.7326127290725708},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7024457454681396},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6875730752944946},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5645479559898376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4860692322254181},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.4844634532928467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44141268730163574},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43302568793296814},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42590439319610596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39158087968826294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32248079776763916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326127290725708},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7024457454681396},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6875730752944946},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5645479559898376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4860692322254181},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.4844634532928467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44141268730163574},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43302568793296814},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42590439319610596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39158087968826294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32248079776763916},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1915251500","https://openalex.org/W2033256038","https://openalex.org/W2066378046","https://openalex.org/W2296014541","https://openalex.org/W2513345070","https://openalex.org/W2577366047","https://openalex.org/W2747467128","https://openalex.org/W2886180730","https://openalex.org/W2913129712","https://openalex.org/W2914699162","https://openalex.org/W2939111082","https://openalex.org/W2963240019","https://openalex.org/W2989539713","https://openalex.org/W3001279689","https://openalex.org/W3008037978","https://openalex.org/W3008174054","https://openalex.org/W3008181812","https://openalex.org/W3015506840","https://openalex.org/W3016234571","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3096815019","https://openalex.org/W3097777922","https://openalex.org/W3109311991","https://openalex.org/W3141961557","https://openalex.org/W3161375121","https://openalex.org/W3169483174","https://openalex.org/W3197976839","https://openalex.org/W3198442913","https://openalex.org/W3198602963","https://openalex.org/W4224308101","https://openalex.org/W4225591000","https://openalex.org/W4225808286","https://openalex.org/W4283745191","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4327845728","https://openalex.org/W6640059789","https://openalex.org/W6732447497","https://openalex.org/W6743477263","https://openalex.org/W6758779242","https://openalex.org/W6769627184","https://openalex.org/W6770212971","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6786752982","https://openalex.org/W6810081322","https://openalex.org/W6810220367"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,21],"study":[4],"the":[5,98,102,117,122],"impact":[6],"of":[7,17,57,101,124,130],"Large-scale":[8],"Language":[9],"Models":[10],"(LLM)":[11],"on":[12,41,62,127],"Automated":[13],"Speech":[14],"Recognition":[15],"(ASR)":[16],"YouTube":[18],"videos,":[19],"which":[20],"use":[22],"as":[23,134],"a":[24,55,69,75,86,89,146,151],"source":[25],"for":[26],"long-form":[27,50],"ASR.":[28],"We":[29,113],"demonstrate":[30],"up":[31,58],"to":[32,59],"8%":[33],"relative":[34,61],"reduction":[35,56],"in":[36,85,106,109,119],"Word":[37],"Error":[38,65],"Eate":[39],"(WER)":[40],"US":[42],"English":[43,48],"(en-us)":[44],"and":[45,54,94,137,143],"code-switched":[46],"Indian":[47],"(en-in)":[49],"ASR":[51],"test":[52],"sets":[53],"30%":[60],"Salient":[63],"Term":[64],"Rate":[66],"(STER)":[67],"over":[68],"strong":[70,147],"first-pass":[71,148],"baseline":[72,149],"that":[73,83,116],"uses":[74],"maximum-entropy":[76],"based":[77],"language":[78],"model.":[79],"Improved":[80],"lattice":[81,87],"processing":[82],"results":[84,105],"with":[88,111,150],"proper":[90],"(non-tree)":[91],"digraph":[92],"topology":[93],"carrying":[95],"context":[96],"from":[97,121],"1-best":[99],"hypothesis":[100],"previous":[103],"segment(s)":[104],"significant":[107],"wins":[108],"rescoring":[110],"LLMs.":[112],"also":[114],"find":[115],"gains":[118],"performance":[120],"combination":[123],"LLMs":[125],"trained":[126],"vast":[128],"quantities":[129],"available":[131],"data":[132],"(such":[133],"C4":[135],"[1])":[136],"conventional":[138],"neural":[139],"LMs":[140],"is":[141],"additive":[142],"significantly":[144],"outperforms":[145],"maximum":[152],"entropy":[153],"LM.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}