{"id":"https://openalex.org/W4392902949","doi":"https://doi.org/10.1109/icassp48485.2024.10447049","title":"Improving Attention-Based End-to-End Speech Recognition by Monotonic Alignment Attention Matrix Reconstruction","display_name":"Improving Attention-Based End-to-End Speech Recognition by Monotonic Alignment Attention Matrix Reconstruction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902949","doi":"https://doi.org/10.1109/icassp48485.2024.10447049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5088311121","display_name":"Ziyang Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Zhuang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570585","display_name":"Kun Zou","orcid":"https://orcid.org/0009-0008-0575-5142"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zou","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093993569","display_name":"Chenfeng Miao","orcid":"https://orcid.org/0009-0006-1986-3035"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chenfeng Miao","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080919889","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-1932-2037"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Fang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261926","display_name":"Tao Wei","orcid":"https://orcid.org/0000-0002-6549-3999"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406497","display_name":"Zijian Li","orcid":"https://orcid.org/0000-0002-3964-3789"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Li","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014243317","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0001-7754-1858"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10546","last_page":"10550"},"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":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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/monotonic-function","display_name":"Monotonic function","score":0.8364275693893433},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7292065620422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6593835353851318},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5713675022125244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5707972645759583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5406188368797302},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46515828371047974},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4615184962749481},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.43353456258773804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4284694790840149},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.333188533782959},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32357504963874817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14382314682006836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08357101678848267}],"concepts":[{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.8364275693893433},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7292065620422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593835353851318},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5713675022125244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5707972645759583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5406188368797302},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46515828371047974},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4615184962749481},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.43353456258773804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284694790840149},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.333188533782959},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32357504963874817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14382314682006836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08357101678848267},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2766219058","https://openalex.org/W2963242190","https://openalex.org/W3008174054","https://openalex.org/W3016010032","https://openalex.org/W3096552437","https://openalex.org/W3097777922","https://openalex.org/W3111562797","https://openalex.org/W3149509723","https://openalex.org/W3162665866","https://openalex.org/W3197478142","https://openalex.org/W4297841485","https://openalex.org/W6623517193","https://openalex.org/W6687566353","https://openalex.org/W6735706088","https://openalex.org/W6739901393","https://openalex.org/W6747158283","https://openalex.org/W6768570733","https://openalex.org/W6787040858","https://openalex.org/W6787300339"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2151749779","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2077314575","https://openalex.org/W3179968364","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2135652437"],"abstract_inverted_index":{"In":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"task,":[5],"the":[6,16,27,53,77,85,92,106,110,113,124],"output":[7],"sequence":[8],"should":[9],"correspond":[10],"to":[11,25,68,97],"a":[12,47,118],"linear":[13],"transcription":[14],"of":[15,20,87,112],"input":[17],"sequence.":[18],"Lots":[19],"works":[21],"have":[22,57],"been":[23],"done":[24],"learn":[26],"monotonic":[28,64,89],"alignment":[29,65],"in":[30,46,49,101],"end-to-end":[31],"(E2E)":[32],"ASR":[33,50,102],"model,":[34],"but":[35],"their":[36],"methods":[37],"mainly":[38],"focus":[39],"on":[40,72,105,132,137],"streaming":[41],"propose":[42,76],"and":[43,91,135],"usually":[44],"result":[45],"decline":[48],"performance.":[51,70],"On":[52],"contrary,":[54],"some":[55],"studies":[56],"shown":[58],"that":[59],"for":[60],"non-streaming":[61],"attention-based":[62],"models,":[63],"is":[66],"beneficial":[67],"model":[69,126],"Based":[71],"this":[73],"motivation,":[74],"we":[75],"enhanced":[78],"Gaussian":[79],"Monotonic":[80],"Alignment":[81],"(e-GMA),":[82],"which":[83],"reduces":[84],"difficulty":[86],"learning":[88],"alignment,":[90],"reconstructed":[93],"attention":[94],"matrix":[95],"leads":[96],"an":[98],"improved":[99],"accuracy":[100],"tasks.":[103],"Experiments":[104],"LibriSpeech":[107],"dataset":[108],"demonstrate":[109],"effectiveness":[111],"proposed":[114,125],"approach.":[115],"Comparing":[116],"with":[117],"strong":[119],"baseline":[120],"obtained":[121],"from":[122],"WeNet,":[123],"yields":[127],"12.2%":[128],"relative":[129],"WER":[130],"reduction":[131],"test-clean":[133],"benchmark":[134],"9.9%":[136],"test-other.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}