{"id":"https://openalex.org/W2981857663","doi":"https://doi.org/10.1109/icassp40776.2020.9054345","title":"Transformer-Based Acoustic Modeling for Hybrid Speech Recognition","display_name":"Transformer-Based Acoustic Modeling for Hybrid Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981857663","doi":"https://doi.org/10.1109/icassp40776.2020.9054345","mag":"2981857663"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054345","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108695360","display_name":"Dieu Ngan Le","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Due Le","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056584611","display_name":"Alex Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Xiao","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028860597","display_name":"Hongzhao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzhao Huang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400244","display_name":"Xiaohui Zhang","orcid":"https://orcid.org/0000-0002-9075-0336"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101984914","display_name":"Frank Zhang","orcid":"https://orcid.org/0000-0001-9946-6502"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Zhang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5100339989"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":27.564,"has_fulltext":false,"cited_by_count":254,"citation_normalized_percentile":{"value":0.99704578,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6874","last_page":"6878"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/transformer","display_name":"Transformer","score":0.7684471607208252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7378689050674438},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6030865907669067},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5786342024803162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5725699067115784},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5175713300704956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.504757285118103},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45067811012268066},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43689700961112976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37756240367889404},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1028662621974945}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7684471607208252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378689050674438},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6030865907669067},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5786342024803162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5725699067115784},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5175713300704956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.504757285118103},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45067811012268066},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43689700961112976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37756240367889404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1028662621974945},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054345","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:1910.09799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09799","pdf_url":"https://arxiv.org/pdf/1910.09799","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09799","pdf_url":"https://arxiv.org/pdf/1910.09799","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1686810756","https://openalex.org/W1920942766","https://openalex.org/W1995562189","https://openalex.org/W2064675550","https://openalex.org/W2097268427","https://openalex.org/W2107878631","https://openalex.org/W2131342762","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2462831000","https://openalex.org/W2520160253","https://openalex.org/W2530876040","https://openalex.org/W2795138957","https://openalex.org/W2798657914","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2896060389","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2911291251","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2944255943","https://openalex.org/W2962760690","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963088785","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964045208","https://openalex.org/W2964084166","https://openalex.org/W2964089206","https://openalex.org/W2972818416","https://openalex.org/W2977728428","https://openalex.org/W2979286696","https://openalex.org/W2981740924","https://openalex.org/W3006827623","https://openalex.org/W3008525923","https://openalex.org/W3015960524","https://openalex.org/W3103005696","https://openalex.org/W4288400010","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6696934422","https://openalex.org/W6712930963","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6769495571"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"We":[0,34,55],"propose":[1],"and":[2,25],"evaluate":[3],"transformer-based":[4,65],"acoustic":[5],"models":[6],"(AMs)":[7],"for":[8,52,92],"hybrid":[9,71],"speech":[10],"recognition.":[11],"Several":[12],"modeling":[13],"choices":[14],"are":[15,104],"discussed":[16],"in":[17,45],"this":[18],"work,":[19],"including":[20],"various":[21],"positional":[22],"embedding":[23],"methods":[24],"an":[26],"iterated":[27],"loss":[28],"to":[29,75],"enable":[30],"training":[31],"deep":[32],"transformers.":[33],"also":[35,105],"present":[36],"a":[37,108],"preliminary":[38],"study":[39],"of":[40],"using":[41],"limited":[42],"right":[43],"context":[44],"transformer":[46],"models,":[47],"which":[48],"makes":[49],"it":[50],"possible":[51],"streaming":[53],"applications.":[54],"demonstrate":[56],"that":[57],"on":[58,100,107],"the":[59,68,79],"widely":[60],"used":[61],"Librispeech":[62],"benchmark,":[63],"our":[64,94],"AM":[66],"outperforms":[67],"best":[69],"published":[70],"result":[72],"by":[73],"19%":[74],"26%":[76],"relative":[77],"when":[78],"standard":[80],"n-gram":[81],"language":[82],"model":[83],"(LM)":[84],"is":[85],"used.":[86],"Combined":[87],"with":[88],"neural":[89],"network":[90],"LM":[91],"rescoring,":[93],"proposed":[95],"approach":[96],"achieves":[97],"state-of-the-art":[98],"results":[99],"Librispeech.":[101],"Our":[102],"findings":[103],"confirmed":[106],"much":[109],"larger":[110],"internal":[111],"dataset.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":52},{"year":2019,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}