{"id":"https://openalex.org/W2900092534","doi":"https://doi.org/10.1109/icassp.2019.8682650","title":"Stream Attention-based Multi-array End-to-end Speech Recognition","display_name":"Stream Attention-based Multi-array End-to-end Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2900092534","doi":"https://doi.org/10.1109/icassp.2019.8682650","mag":"2900092534"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"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":["The Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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":["The Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University","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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sri Harish Mallidi","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"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":["The Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"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":["The Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6242,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92646367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7105","last_page":"7109"},"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":0.9998999834060669,"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":0.9998000264167786,"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":0.7922061085700989},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6924009323120117},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6920520663261414},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6691944599151611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5819495916366577},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5255473852157593},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5206855535507202},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4514084458351135},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4269936978816986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35287660360336304},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3500574231147766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30317628383636475},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07012322545051575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922061085700989},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6924009323120117},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6920520663261414},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6691944599151611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5819495916366577},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5255473852157593},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5206855535507202},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4514084458351135},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4269936978816986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35287660360336304},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3500574231147766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30317628383636475},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07012322545051575},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1904457459","https://openalex.org/W2102113734","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2289690552","https://openalex.org/W2327501763","https://openalex.org/W2470673105","https://openalex.org/W2526425061","https://openalex.org/W2532854561","https://openalex.org/W2559260703","https://openalex.org/W2584992898","https://openalex.org/W2600628583","https://openalex.org/W2627092829","https://openalex.org/W2746095516","https://openalex.org/W2766219058","https://openalex.org/W2767071179","https://openalex.org/W2884797218","https://openalex.org/W2886180730","https://openalex.org/W2889367162","https://openalex.org/W2889508099","https://openalex.org/W2894835365","https://openalex.org/W2899640612","https://openalex.org/W2900070823","https://openalex.org/W2900091092","https://openalex.org/W2900440209","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2963064586","https://openalex.org/W2963211739","https://openalex.org/W2963407669","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6678809451","https://openalex.org/W6735168207","https://openalex.org/W6756137172"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"using":[4,120],"multiple":[5],"microphone":[6],"arrays":[7],"has":[8,133],"achieved":[9,134],"great":[10],"success":[11],"in":[12,30,44,56,145],"the":[13,20,35,45,73,93,103,106,121,126,130,146],"far-field":[14],"robustness.":[15],"Taking":[16],"advantage":[17],"of":[18,37,75,83,92,141],"all":[19],"information":[21,63],"that":[22],"each":[23],"array":[24],"shares":[25],"and":[26,70,78,116,143],"contributes":[27],"is":[28,54,88,99,151],"crucial":[29],"this":[31,57],"task.":[32],"Motivated":[33],"by":[34,67],"advances":[36],"joint":[38],"Connectionist":[39],"Temporal":[40],"Classification":[41],"(CTC)/attention":[42],"mechanism":[43],"End-to-End":[46],"(E2E)":[47],"ASR,":[48],"a":[49,85],"stream":[50,97],"attention-based":[51],"multi-array":[52,118],"framework":[53,132],"proposed":[55,131],"work.":[58],"Microphone":[59],"arrays,":[60],"acting":[61],"as":[62,156],"streams,":[64],"are":[65],"activated":[66],"separate":[68],"encoders":[69],"decoded":[71],"under":[72],"instruction":[74],"both":[76],"CTC":[77],"attention":[79,95,98],"networks.":[80],"In":[81],"terms":[82],"attention,":[84],"hierarchical":[86],"structure":[87],"adopted.":[89],"On":[90],"top":[91],"regular":[94],"networks,":[96],"introduced":[100],"to":[101],"steer":[102],"decoder":[104],"toward":[105],"most":[107],"informative":[108],"encoders.":[109],"Experiments":[110],"have":[111],"been":[112],"conducted":[113],"on":[114],"AMI":[115],"DIRHA":[117],"corpora":[119],"encoder-decoder":[122],"architecture.":[123],"Compared":[124],"with":[125],"best":[127],"single-array":[128],"results,":[129],"relative":[135],"Word":[136],"Error":[137],"Rates":[138],"(WERs)":[139],"reduction":[140],"3.7%":[142],"9.7%":[144],"two":[147],"datasets,":[148],"respectively,":[149],"which":[150],"better":[152],"than":[153],"conventional":[154],"strategies":[155],"well.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}