{"id":"https://openalex.org/W3011956499","doi":"https://doi.org/10.1109/icassp40776.2020.9053600","title":"Hybrid Autoregressive Transducer (HAT)","display_name":"Hybrid Autoregressive Transducer (HAT)","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3011956499","doi":"https://doi.org/10.1109/icassp40776.2020.9053600","mag":"3011956499"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.07705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","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 (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","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/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyril Allauzen","raw_affiliation_strings":["AT&T (United States), Bedminster, United States"],"affiliations":[{"raw_affiliation_string":"AT&T (United States), Bedminster, United States","institution_ids":["https://openalex.org/I1283103587"]}]},{"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,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040131037"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.4078,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6844382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6139","last_page":"6143"},"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":0.9993000030517578,"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":0.9987999796867371,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8208606243133545},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7213172316551208},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.7174025774002075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6842355728149414},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5940099954605103},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.593912661075592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4836472272872925},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48256009817123413},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46818530559539795},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43411946296691895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41445302963256836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21348142623901367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12640082836151123},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.06768393516540527}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8208606243133545},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7213172316551208},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.7174025774002075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6842355728149414},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5940099954605103},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.593912661075592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4836472272872925},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48256009817123413},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46818530559539795},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43411946296691895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41445302963256836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21348142623901367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12640082836151123},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.06768393516540527},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.07705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.07705","pdf_url":"https://arxiv.org/pdf/2003.07705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3011956499","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.07705.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2003.07705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.07705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},{"id":"doi:10.17023/edhe-3z60","is_oa":true,"landing_page_url":"https://doi.org/10.17023/edhe-3z60","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.07705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.07705","pdf_url":"https://arxiv.org/pdf/2003.07705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"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/W3011956499.pdf","grobid_xml":"https://content.openalex.org/works/W3011956499.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W30564313","https://openalex.org/W1489125746","https://openalex.org/W1753482797","https://openalex.org/W1828163288","https://openalex.org/W1877570817","https://openalex.org/W1895481600","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1966812932","https://openalex.org/W1990005915","https://openalex.org/W2005076803","https://openalex.org/W2042098456","https://openalex.org/W2046932483","https://openalex.org/W2056786202","https://openalex.org/W2064675550","https://openalex.org/W2114016253","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2156373089","https://openalex.org/W2157331557","https://openalex.org/W2158373110","https://openalex.org/W2172140247","https://openalex.org/W2176263492","https://openalex.org/W2250489405","https://openalex.org/W2327501763","https://openalex.org/W2395440424","https://openalex.org/W2407778575","https://openalex.org/W2520160253","https://openalex.org/W2745596852","https://openalex.org/W2747467128","https://openalex.org/W2748584437","https://openalex.org/W2748679025","https://openalex.org/W2771551388","https://openalex.org/W2886180730","https://openalex.org/W2912492482","https://openalex.org/W2939111082","https://openalex.org/W2950903920","https://openalex.org/W2951327905","https://openalex.org/W2962760690","https://openalex.org/W2963382687","https://openalex.org/W2963537349","https://openalex.org/W2963827914","https://openalex.org/W2963850025","https://openalex.org/W2963920996","https://openalex.org/W2964107261","https://openalex.org/W6601268434","https://openalex.org/W6637698695","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6685322675","https://openalex.org/W6728910023","https://openalex.org/W6732447497","https://openalex.org/W6746554617","https://openalex.org/W6746574493","https://openalex.org/W6759008529"],"related_works":["https://openalex.org/W3202419788","https://openalex.org/W3156902660","https://openalex.org/W2914151612","https://openalex.org/W3093733783","https://openalex.org/W3112470437","https://openalex.org/W3095292526","https://openalex.org/W3031064774","https://openalex.org/W2134742194","https://openalex.org/W1984067647","https://openalex.org/W2606052883","https://openalex.org/W3177132412","https://openalex.org/W2963103134","https://openalex.org/W1544673079","https://openalex.org/W2981857663","https://openalex.org/W3154353420","https://openalex.org/W3204687321","https://openalex.org/W2288648150","https://openalex.org/W2291681054","https://openalex.org/W2936399153","https://openalex.org/W2468324704"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"and":[3],"evaluates":[4],"the":[5,17,33,36,77],"hybrid":[6],"autoregressive":[7],"transducer":[8],"(HAT)":[9],"model,":[10],"a":[11,29,63],"time-synchronous":[12],"encoder-decoder":[13],"model":[14,27,39,52,61],"that":[15,40],"preserves":[16],"modularity":[18],"of":[19,35],"conventional":[20],"automatic":[21],"speech":[22],"recognition":[23],"systems.":[24],"The":[25],"HAT":[26],"provides":[28],"way":[30],"to":[31,44,76],"measure":[32],"quality":[34],"internal":[37],"language":[38,51],"can":[41],"be":[42],"used":[43],"decide":[45],"whether":[46],"inference":[47],"with":[48],"an":[49],"external":[50],"is":[53],"beneficial":[54],"or":[55],"not.":[56],"We":[57],"evaluate":[58],"our":[59],"proposed":[60],"on":[62],"large-scale":[64],"voice":[65],"search":[66],"task.":[67],"Our":[68],"experiments":[69],"show":[70],"significant":[71],"improvements":[72],"in":[73],"WER":[74],"compared":[75],"state-of-the-art":[78],"approaches":[79],"<sup":[80],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[81],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[82],".":[83]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}