{"id":"https://openalex.org/W2775766866","doi":"https://doi.org/10.1109/icassp.2018.8462682","title":"An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model","display_name":"An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2775766866","doi":"https://doi.org/10.1109/icassp.2018.8462682","mag":"2775766866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.01996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023098355","display_name":"Anjuli Kannan","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":"Anjuli Kannan","raw_affiliation_strings":["Google, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","raw_affiliation_strings":["Google, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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/A5111455517","display_name":"Patrick Nguyen","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":"Patrick Nguyen","raw_affiliation_strings":["Google, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"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":"ZhiJeng Chen","raw_affiliation_strings":["Google, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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/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, Inc., USA","Google Inc., USA"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.0187,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81308786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5828"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.9976999759674072,"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/language-model","display_name":"Language model","score":0.7530738711357117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7318333387374878},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7240543365478516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5686619281768799},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5374683737754822},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.536735475063324},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.5326209664344788},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.522860050201416},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5195032358169556},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5132744312286377},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5032088160514832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496316909790039},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4436846971511841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4430438280105591},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22123825550079346},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.13932177424430847},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1341344118118286}],"concepts":[{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7530738711357117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318333387374878},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7240543365478516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5686619281768799},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5374683737754822},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.536735475063324},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5326209664344788},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.522860050201416},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5195032358169556},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5132744312286377},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5032088160514832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496316909790039},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4436846971511841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4430438280105591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22123825550079346},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.13932177424430847},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1341344118118286},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.01996","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.01996","pdf_url":"https://arxiv.org/pdf/1712.01996","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2775766866","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1712.01996.pdf","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1712.01996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.01996","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.01996","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.01996","pdf_url":"https://arxiv.org/pdf/1712.01996","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2775766866.pdf","grobid_xml":"https://content.openalex.org/works/W2775766866.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1524333225","https://openalex.org/W1566256432","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2064675550","https://openalex.org/W2121879602","https://openalex.org/W2259472270","https://openalex.org/W2296545762","https://openalex.org/W2410539690","https://openalex.org/W2515439472","https://openalex.org/W2525778437","https://openalex.org/W2577366047","https://openalex.org/W2748679025","https://openalex.org/W2750499125","https://openalex.org/W2962826786","https://openalex.org/W2962988733","https://openalex.org/W2963414781","https://openalex.org/W2963920996","https://openalex.org/W6629052376","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6640059789","https://openalex.org/W6676562027","https://openalex.org/W6692563993","https://openalex.org/W6714264011","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6743440867","https://openalex.org/W6743477263","https://openalex.org/W6747398299"],"related_works":["https://openalex.org/W2963240019","https://openalex.org/W2109886035","https://openalex.org/W2962961016","https://openalex.org/W3007905516","https://openalex.org/W2968359484","https://openalex.org/W2754219472","https://openalex.org/W2937148911","https://openalex.org/W2801798988","https://openalex.org/W2100768664","https://openalex.org/W3090123943","https://openalex.org/W2057822435","https://openalex.org/W2785860501","https://openalex.org/W1561506132","https://openalex.org/W1710082047","https://openalex.org/W2891628540","https://openalex.org/W2336585117","https://openalex.org/W749916933","https://openalex.org/W2111000581","https://openalex.org/W2406482790","https://openalex.org/W2950523597"],"abstract_inverted_index":{"Attention-based":[0],"sequence-to-sequence":[1,121],"models":[2],"for":[3,126],"automatic":[4],"speech":[5],"recognition":[6],"jointly":[7],"train":[8],"an":[9,38,103],"acoustic":[10],"model,":[11,13,122],"language":[12,19,40,55,82],"and":[14,87],"alignment":[15],"mechanism.":[16],"Thus,":[17],"the":[18,32,61,69,97,124],"model":[20,41,56],"component":[21],"is":[22],"only":[23],"trained":[24,54],"on":[25],"transcribed":[26],"audio-text":[27],"pairs.":[28],"This":[29],"leads":[30],"to":[31,48],"use":[33,98],"of":[34,60,71,77,81,99],"shallow":[35,72,100],"fusion":[36,46,73,101],"with":[37,51,102,106],"external":[39],"at":[42,57],"inference":[43],"time.":[44],"Shallow":[45],"refers":[47],"log-linear":[49],"interpolation":[50],"a":[52,75,109],"separately":[53],"each":[58],"step":[59],"beam":[62],"search.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,94],"investigate":[68],"behavior":[70],"across":[74],"range":[76],"conditions:":[78],"different":[79,84,88],"types":[80],"models,":[83],"decoding":[85],"units,":[86],"tasks.":[89],"On":[90],"Google":[91],"Voice":[92],"Search,":[93],"demonstrate":[95],"that":[96],"neural":[104],"LM":[105],"wordpieces":[107],"yields":[108],"9.1%":[110],"relative":[111],"word":[112],"error":[113],"rate":[114],"reduction":[115],"(WERR)":[116],"over":[117],"our":[118],"competitive":[119],"attention-based":[120],"obviating":[123],"need":[125],"second-pass":[127],"rescoring.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2022-10-05T00:00:00"}