{"id":"https://openalex.org/W4391021736","doi":"https://doi.org/10.1109/asru57964.2023.10389720","title":"Acoustic Model Fusion For End-to-End Speech Recognition","display_name":"Acoustic Model Fusion For End-to-End Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021736","doi":"https://doi.org/10.1109/asru57964.2023.10389720"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5040740925","display_name":"Zhihong Lei","orcid":"https://orcid.org/0000-0001-7846-3417"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhihong Lei","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086280874","display_name":"Mingbin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingbin Xu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054574376","display_name":"Shiyi Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shiyi Han","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842894","display_name":"Leo Liu","orcid":"https://orcid.org/0009-0008-1720-8533"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leo Liu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011008665","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0003-4819-373X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhen Huang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110640042","display_name":"Tim Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Ng","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320635","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0001-9738-604X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048094198","display_name":"Ernest Pusateri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ernest Pusateri","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110926453","display_name":"Mirko Hannemann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirko Hannemann","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050980161","display_name":"Yaqiao Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaqiao Deng","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067041166","display_name":"Man-Hung Siu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Man-Hung Siu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.9678,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81311594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961985468864441},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7752087116241455},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6654875874519348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6435732841491699},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5312848687171936},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5213621854782104},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5141792297363281},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5019464492797852},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47965243458747864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46525058150291443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44016724824905396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3279606103897095},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28866249322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961985468864441},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7752087116241455},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6654875874519348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6435732841491699},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5312848687171936},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5213621854782104},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5141792297363281},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5019464492797852},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47965243458747864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46525058150291443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44016724824905396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3279606103897095},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28866249322891235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2888779557","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963362078","https://openalex.org/W2963454111","https://openalex.org/W3008037978","https://openalex.org/W3015480556","https://openalex.org/W3097777922","https://openalex.org/W3152221657","https://openalex.org/W3163793923","https://openalex.org/W3197478142","https://openalex.org/W4221167707","https://openalex.org/W4385245566","https://openalex.org/W4392903347","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6679434410","https://openalex.org/W6739879593","https://openalex.org/W6739901393"],"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/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2244609359"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,45,137,165],"deep":[3],"learning":[4],"and":[5,17,40],"automatic":[6],"speech":[7],"recognition":[8],"(ASR)":[9],"have":[10,132],"enabled":[11],"the":[12,19,36,41,68,77,91,97,103,110,117,123,138],"end-to-end":[13],"(E2E)":[14],"ASR":[15,32],"system":[16,56,70,119],"boosted":[18],"accuracy":[20],"to":[21,73,89,96,120,148],"a":[22,46,59,134],"new":[23],"level.":[24],"The":[25],"E2E":[26,69,118],"systems":[27],"implicitly":[28],"model":[29,38,43],"all":[30],"conventional":[31],"components,":[33],"such":[34,85],"as":[35,86],"acoustic":[37],"(AM)":[39],"language":[42],"(LM),":[44],"single":[47],"network":[48],"trained":[49,62],"on":[50,64],"audio-text":[51],"pairs.":[52],"Despite":[53],"this":[54,128,158],"simpler":[55],"architecture,":[57],"fusing":[58],"separate":[60],"LM,":[61],"exclusively":[63],"text":[65],"corpora,":[66],"into":[67,116],"has":[71],"proven":[72],"be":[74],"beneficial.":[75],"However,":[76],"application":[78],"of":[79,105,112,146],"LM":[80,106],"fusion":[81,160],"presents":[82],"certain":[83],"drawbacks,":[84],"its":[87],"inability":[88],"address":[90,122],"domain":[92,124],"mismatch":[93],"issue":[94],"inherent":[95],"internal":[98],"AM.":[99],"Drawing":[100],"inspiration":[101],"from":[102],"concept":[104],"fusion,":[107],"we":[108,131],"propose":[109],"integration":[111],"an":[113,143],"external":[114],"AM":[115,159],"better":[121],"mismatch.":[125],"By":[126],"implementing":[127],"novel":[129],"approach,":[130],"achieved":[133],"significant":[135],"reduction":[136],"word":[139],"error":[140],"rate,":[141],"with":[142],"impressive":[144],"drop":[145],"up":[147],"14.3%":[149],"across":[150],"varied":[151],"test":[152],"sets.":[153],"We":[154],"also":[155],"discovered":[156],"that":[157],"approach":[161],"is":[162],"particularly":[163],"beneficial":[164],"enhancing":[166],"named":[167],"entity":[168],"recognition.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}