{"id":"https://openalex.org/W3096123040","doi":"https://doi.org/10.21437/interspeech.2020-1972","title":"Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition","display_name":"Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096123040","doi":"https://doi.org/10.21437/interspeech.2020-1972","mag":"3096123040"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1972","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Speech Lab, Alibaba DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024223042","display_name":"Zhifu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Zhifu Gao","raw_affiliation_strings":["Speech Lab, Alibaba DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088820402","display_name":"Haoneng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoneng Luo","raw_affiliation_strings":["ASLP@NPU, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP@NPU, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058896884","display_name":"Ming Lei","orcid":"https://orcid.org/0000-0002-5712-3285"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Ming Lei","raw_affiliation_strings":["Speech Lab, Alibaba DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073887901","display_name":"Jie Gao","orcid":"https://orcid.org/0000-0002-5601-2858"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Jie Gao","raw_affiliation_strings":["Speech Lab, Alibaba DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Speech Lab, Alibaba DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["ASLP@NPU, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP@NPU, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3828,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85235992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2142","last_page":"2146"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9976000189781189,"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":0.8308907747268677},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.809532105922699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351943612098694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3200443983078003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28809142112731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308907747268677},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.809532105922699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351943612098694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3200443983078003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28809142112731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1972","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1828163288","https://openalex.org/W2102113734","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2590320937","https://openalex.org/W2605141709","https://openalex.org/W2745439869","https://openalex.org/W2767601419","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2953384591","https://openalex.org/W2963242190","https://openalex.org/W2963308316","https://openalex.org/W2972439411","https://openalex.org/W2972451902","https://openalex.org/W2972686346","https://openalex.org/W2972818416","https://openalex.org/W2972977747","https://openalex.org/W2972995428","https://openalex.org/W2981696585","https://openalex.org/W3012775809","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3097580812","https://openalex.org/W4294619417","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Recently,":[0],"streaming":[1,25,86],"end-to-end":[2],"automatic":[3],"speech":[4,99],"recognition":[5,100],"(E2E-ASR)":[6],"has":[7],"gained":[8],"more":[9,11],"and":[10,43,94],"attention.Many":[12],"efforts":[13],"have":[14],"been":[15],"paid":[16],"to":[17,55,61,69,77,82,130],"turn":[18],"the":[19,57,71,90,109,116,131,138],"non-streaming":[20],"attention-based":[21],"E2E-ASR":[22,34],"system":[23,35,112],"into":[24],"architecture.In":[26],"this":[27],"work,":[28],"we":[29],"propose":[30],"a":[31,44,63,123],"novel":[32],"online":[33,143],"by":[36],"using":[37],"Streaming":[38],"Chunk-Aware":[39],"Multihead":[40],"Attention":[41],"(SCAMA)":[42],"latency":[45,58],"control":[46,56,70],"memory":[47],"equipped":[48],"self-attention":[49],"network":[50],"(LC-SAN-M).LC-SAN-M":[51],"uses":[52],"chunk-level":[53],"input":[54],"of":[59,73,128,133],"encoder.As":[60],"SCAMA,":[62],"jointly":[64],"trained":[65],"predictor":[66],"is":[67,137],"used":[68],"output":[72,84],"encoder":[74],"when":[75],"feeding":[76],"decoder,":[78],"which":[79,136],"enables":[80],"decoder":[81],"generate":[83],"in":[85],"manner.Experimental":[87],"results":[88],"on":[89],"open":[91],"170-hour":[92],"AISHELL-1":[93,117],"an":[95],"industrial-level":[96],"20000-hour":[97],"Mandarin":[98],"tasks":[101],"show":[102],"that":[103],"our":[104,119,134],"approach":[105],"can":[106],"significantly":[107],"outperform":[108],"MoChA-based":[110],"baseline":[111],"under":[113],"comparable":[114],"setup.On":[115],"task,":[118],"proposed":[120],"method":[121],"achieves":[122],"character":[124],"error":[125],"rate":[126],"(CER)":[127],"7.39%,":[129],"best":[132,139],"knowledge,":[135],"published":[140],"performance":[141],"for":[142],"ASR.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}