{"id":"https://openalex.org/W3042416212","doi":"https://doi.org/10.1109/taslp.2020.3009477","title":"Modular End-to-End Automatic Speech Recognition Framework for Acoustic-to-Word Model","display_name":"Modular End-to-End Automatic Speech Recognition Framework for Acoustic-to-Word Model","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3042416212","doi":"https://doi.org/10.1109/taslp.2020.3009477","mag":"3042416212"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3009477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3009477","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100734777","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0003-3067-8333"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3067-8333","affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4400-5340","affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348721","display_name":"Hao Li","orcid":"https://orcid.org/0009-0005-4319-9026"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067488078","display_name":"Mingkun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkun Huang","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Lu","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"The authors are with SpeechLab, Department of Computer Science and Engineering, and MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.3406,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85128033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2174","last_page":"2183"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8089509010314941},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7411126494407654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7286193370819092},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6530275344848633},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6013221740722656},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5871427655220032},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5789987444877625},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5416600704193115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48975229263305664},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4726114571094513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4659591317176819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3398582339286804},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.17032179236412048},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09981730580329895},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0665769875049591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089509010314941},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7411126494407654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7286193370819092},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6530275344848633},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6013221740722656},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5871427655220032},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5789987444877625},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5416600704193115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48975229263305664},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4726114571094513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659591317176819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3398582339286804},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.17032179236412048},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09981730580329895},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0665769875049591},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3009477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3009477","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2915035755","display_name":null,"funder_award_id":"2017YFB1002102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1513820424","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2032005922","https://openalex.org/W2046932483","https://openalex.org/W2077574412","https://openalex.org/W2100772283","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2140539590","https://openalex.org/W2143612262","https://openalex.org/W2156373089","https://openalex.org/W2166637769","https://openalex.org/W2186615578","https://openalex.org/W2208299922","https://openalex.org/W2250539671","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2407080277","https://openalex.org/W2507132449","https://openalex.org/W2515753980","https://openalex.org/W2516196286","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2748584437","https://openalex.org/W2883586237","https://openalex.org/W2884483159","https://openalex.org/W2886180730","https://openalex.org/W2888779557","https://openalex.org/W2888884590","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2962961016","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963303028","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W2964012862","https://openalex.org/W2964308564","https://openalex.org/W3007227084","https://openalex.org/W3104486441","https://openalex.org/W4299881631","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6686509673","https://openalex.org/W6688039610","https://openalex.org/W6696934422","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W50892825","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"systems":[2,22,73],"have":[3],"played":[4],"a":[5,84,106,168,197],"more":[6,8],"and":[7,16,105,165,190],"important":[9],"role":[10],"in":[11,192],"automatic":[12],"speech":[13],"recognition":[14],"(ASR)":[15],"achieved":[17],"great":[18],"performance.":[19],"However,":[20],"E2E":[21,71,77,87,94,140,179,199,212],"recognize":[23],"output":[24],"word":[25,216],"sequences":[26],"directly":[27],"with":[28,186],"the":[29,51,76,131,138,147,152,156,159,176,193,205,210],"input":[30],"acoustic":[31,40,116,148],"feature,":[32],"which":[33],"can":[34,126,182],"only":[35,146],"be":[36,127,163,183],"trained":[37,114,185],"on":[38,115,204],"limited":[39],"data.":[41],"The":[42,63,92,110],"extra":[43,66,119,187],"text":[44,67,124,188],"data":[45,68,120,125,136,189],"is":[46,90,113],"widely":[47],"used":[48,128],"to":[49,69,129,143],"improve":[50],"results":[52,203],"of":[53,65,98],"traditional":[54],"artificial":[55],"neural":[56],"network-hidden":[57],"Markov":[58],"model":[59,104,112,144,213],"(ANN-HMM)":[60],"hybrid":[61],"systems.":[62],"involving":[64],"standard":[70,169,198,221],"ASR":[72,88,95,141,180,200],"may":[74],"break":[75],"property":[78],"during":[79],"decoding.":[80],"In":[81,173],"this":[82],"paper,":[83],"novel":[85],"modular":[86,93,139,178,211],"system":[89,96,142,181],"proposed.":[91],"consists":[97],"two":[99,160],"parts:":[100],"an":[101],"acoustic-to-phoneme":[102],"(A2P)":[103],"phoneme-to-word":[107],"(P2W)":[108],"model.":[109,133,172],"A2P":[111],"data,":[117],"while":[118],"including":[121],"large":[122],"scale":[123],"train":[130],"P2W":[132],"This":[134],"additional":[135],"enables":[137],"not":[145],"part":[149],"but":[150],"also":[151],"language":[153],"part.":[154],"During":[155],"decoding":[157],"phase,":[158],"models":[161],"will":[162],"integrated":[164],"act":[166],"as":[167,196],"acoustic-to-word":[170],"(A2W)":[171],"other":[174],"words,":[175],"proposed":[177],"easily":[184],"decoded":[191],"same":[194],"way":[195],"system.":[201],"Experimental":[202],"Switchboard":[206],"corpus":[207],"show":[208],"that":[209],"achieves":[214],"better":[215],"error":[217],"rate":[218],"(WER)":[219],"than":[220],"A2W":[222],"models.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}