{"id":"https://openalex.org/W2995025901","doi":"https://doi.org/10.1109/taslp.2019.2959721","title":"Multi-Stream End-to-End Speech Recognition","display_name":"Multi-Stream End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-12-13","ids":{"openalex":"https://openalex.org/W2995025901","doi":"https://doi.org/10.1109/taslp.2019.2959721","mag":"2995025901"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2959721","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.1109/taslp.2019.2959721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":["Johns Hopkins University (JHU), Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (JHU), Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063074341","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-8837-401X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Johns Hopkins University (JHU), Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (JHU), Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047596805","display_name":"Sri Harish Mallidi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sri Harish Mallidi","raw_affiliation_strings":["Amazon, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University (JHU), Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (JHU), Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Johns Hopkins University (JHU), Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (JHU), Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.393,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.815562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":92},"biblio":{"volume":"28","issue":null,"first_page":"646","last_page":"655"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9998,"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":0.9996,"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/robustness","display_name":"Robustness","score":0.5826107},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.55336624},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.44921613},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43392432}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.75605583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74646866},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5826107},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.55336624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.53847206},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.50501925},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.46198258},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.44921613},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43392432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37956005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36810154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35108966},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17426312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.089820206},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2959721","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.08041","pdf_url":"https://arxiv.org/pdf/1906.08041","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2959721","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.61,"display_name":"Peace, justice, and strong institutions"}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"1704170"},{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"1743616"}],"datasets":[],"versions":[],"referenced_works_count":62,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W1904457459","https://openalex.org/W2102113734","https://openalex.org/W2103621378","https://openalex.org/W2106557043","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2144121180","https://openalex.org/W2144499799","https://openalex.org/W2148613904","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2289690552","https://openalex.org/W2327501763","https://openalex.org/W2397147568","https://openalex.org/W2470673105","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2532854561","https://openalex.org/W2559260703","https://openalex.org/W2577366047","https://openalex.org/W2584992898","https://openalex.org/W2593910181","https://openalex.org/W2605141709","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2745439869","https://openalex.org/W2746095516","https://openalex.org/W2766219058","https://openalex.org/W2767071179","https://openalex.org/W2767601419","https://openalex.org/W2775161621","https://openalex.org/W2776984718","https://openalex.org/W2884797218","https://openalex.org/W2886025712","https://openalex.org/W2886180730","https://openalex.org/W2886319145","https://openalex.org/W2889282842","https://openalex.org/W2889367162","https://openalex.org/W2889508099","https://openalex.org/W2894835365","https://openalex.org/W2900070823","https://openalex.org/W2900092534","https://openalex.org/W2900440209","https://openalex.org/W2904113148","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963064586","https://openalex.org/W2963071736","https://openalex.org/W2963211739","https://openalex.org/W2963312585","https://openalex.org/W2963403868","https://openalex.org/W2963407669","https://openalex.org/W2963590118","https://openalex.org/W2964272710","https://openalex.org/W4294619417","https://openalex.org/W4385245566","https://openalex.org/W854541894"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2221419418","https://openalex.org/W2136453575","https://openalex.org/W1997922073","https://openalex.org/W1761388607","https://openalex.org/W1732468982"],"abstract_inverted_index":{"Attention-based":[0],"methods":[1],"and":[2,35,106,114,131,153,165,213,217],"Connectionist":[3],"Temporal":[4],"Classification":[5],"(CTC)":[6],"network":[7,90],"have":[8,103],"been":[9,104],"promising":[10],"research":[11],"directions":[12],"for":[13],"end-to-end":[14],"(E2E)":[15],"Automatic":[16],"Speech":[17],"Recognition":[18],"(ASR).":[19],"The":[20,177],"joint":[21,36,48],"CTC/Attention":[22,49],"model":[23],"has":[24,206],"achieved":[25,207],"great":[26],"success":[27],"by":[28,56,194],"utilizing":[29],"both":[30],"architectures":[31],"during":[32],"multi-task":[33],"training":[34],"decoding.":[37],"In":[38,120],"this":[39],"article,":[40],"we":[41],"present":[42],"a":[43],"multi-stream":[44],"framework":[45,102,113,179,205],"based":[46],"on":[47,148],"E2E":[50],"ASR":[51,185],"with":[52,126,198],"parallel":[53,137],"streams":[54],"represented":[55],"separate":[57,88,132,195],"encoders":[58,125],"aiming":[59],"to":[60,78,93,96,138],"capture":[61],"diverse":[62],"information.":[63],"On":[64],"top":[65],"of":[66,163,169,211],"the":[67,71,80,83,166,172,183,199,203],"regular":[68],"attention":[69],"networks,":[70],"Hierarchical":[72],"Attention":[73],"Network":[74],"(HAN)":[75],"is":[76,91],"introduced":[77],"steer":[79],"decoder":[81],"toward":[82],"most":[84],"informative":[85],"encoders.":[86,196],"A":[87],"CTC":[89,133],"assigned":[92],"each":[94],"stream":[95],"force":[97],"monotonic":[98],"alignments.":[99],"Two":[100],"representative":[101],"proposed":[105,204],"discussed,":[107],"which":[108,191,222],"are":[109,146,192],"Multi-Encoder":[110,115],"Multi-Resolution":[111],"(MEM-Res)":[112],"Multi-Array":[116],"(MEM-Array)":[117],"framework,":[118,122],"respectively.":[119],"MEM-Res":[121],"two":[123],"heterogeneous":[124],"different":[127],"architectures,":[128],"temporal":[129],"resolutions":[130],"networks":[134],"work":[135],"in":[136,156,171,215],"extract":[139],"complementary":[140],"information":[141],"from":[142],"same":[143],"acoustics.":[144],"Experiments":[145],"conducted":[147],"Wall":[149],"Street":[150],"Journal":[151],"(WSJ)":[152],"CHiME-4,":[154],"resulting":[155],"relative":[157,208],"Word":[158],"Error":[159],"Rate":[160],"(WER)":[161],"reduction":[162,210],"18.0-32.1%":[164],"best":[167,200],"WER":[168,209],"3.6%":[170],"WSJ":[173],"eval92":[174],"test":[175],"set.":[176],"MEM-Array":[178],"aims":[180],"at":[181],"improving":[182],"far-field":[184],"robustness":[186],"using":[187],"multiple":[188],"microphone":[189],"arrays":[190],"activated":[193],"Compared":[197],"single-array":[201],"results,":[202],"3.7%":[212],"9.7%":[214],"AMI":[216],"DIRHA":[218],"multi-array":[219],"corpora,":[220],"respectively,":[221],"also":[223],"outperforms":[224],"conventional":[225],"fusion":[226],"strategies.":[227]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2995025901","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2025-01-16T02:11:31.983927","created_date":"2019-12-26"}