{"id":"https://openalex.org/W2767071179","doi":"https://doi.org/10.1109/jstsp.2017.2764276","title":"Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming","display_name":"Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming","publication_year":2017,"publication_date":"2017-10-18","ids":{"openalex":"https://openalex.org/W2767071179","doi":"https://doi.org/10.1109/jstsp.2017.2764276","mag":"2767071179"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2764276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2764276","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal 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/A5103151157","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-5422-6617"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["Doshisha University, Kyotanabe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5422-6617","affiliations":[{"raw_affiliation_string":"Doshisha University, Kyotanabe, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"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/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":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"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, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4560-8039","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"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":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057945477","display_name":"Xiong Xiao","orcid":"https://orcid.org/0000-0003-4471-7946"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1338,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.98559017,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"1274","last_page":"1288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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":0.9991000294685364,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8996284008026123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.81172776222229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6378561854362488},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.547245979309082},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.514575183391571},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49866795539855957},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4808581471443176},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4286603033542633},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4117676615715027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3658371567726135},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16304096579551697},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09770461916923523}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8996284008026123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81172776222229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6378561854362488},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.547245979309082},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.514575183391571},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49866795539855957},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4808581471443176},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4286603033542633},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4117676615715027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3658371567726135},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16304096579551697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09770461916923523},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2017.2764276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2764276","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1586532344","https://openalex.org/W1815076433","https://openalex.org/W2027499299","https://openalex.org/W2066218102","https://openalex.org/W2102113734","https://openalex.org/W2103088716","https://openalex.org/W2130361043","https://openalex.org/W2130942839","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2193413348","https://openalex.org/W2242685705","https://openalex.org/W2264763718","https://openalex.org/W2288645994","https://openalex.org/W2296167893","https://openalex.org/W2327501763","https://openalex.org/W2398042854","https://openalex.org/W2398826216","https://openalex.org/W2398972335","https://openalex.org/W2506203739","https://openalex.org/W2516857479","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2594647430","https://openalex.org/W2595142274","https://openalex.org/W2600628583","https://openalex.org/W2608712415","https://openalex.org/W2627092829","https://openalex.org/W2636483419","https://openalex.org/W2640112133","https://openalex.org/W2702006285","https://openalex.org/W2714487941","https://openalex.org/W2954695182","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963807216","https://openalex.org/W2966212213","https://openalex.org/W3112742522","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6638545294","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6693093084","https://openalex.org/W6712560600","https://openalex.org/W6734797129","https://openalex.org/W6735168207","https://openalex.org/W6766475400","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3179968364","https://openalex.org/W2097963413","https://openalex.org/W876328409","https://openalex.org/W2396048001","https://openalex.org/W2905188205","https://openalex.org/W1559044324"],"abstract_inverted_index":{"This":[0,140],"paper":[1],"proposes":[2],"a":[3,19,72,87,215,246],"unified":[4],"architecture":[5,59,141],"for":[6,81],"end-to-end":[7,25,29,83,94,111,126,155,162,201,209,241],"automatic":[8],"speech":[9,133,138,143],"recognition":[10],"(ASR)":[11],"to":[12,40,107,135,148,152,160],"encompass":[13],"microphone-array":[14],"signal":[15,134],"processing":[16],"such":[17,62,118],"as":[18,37,65],"state-of-the-art":[20],"neural":[21,46,74,233],"beamformer":[22,217],"within":[23],"the":[24,28,78,82,154,168,176,183,207,240],"framework.":[26],"Recently,":[27],"ASR":[30,58,63,84,100,121,127,146,156,185,242],"paradigm":[31],"has":[32],"attracted":[33],"great":[34],"research":[35],"interest":[36],"an":[38,161],"alternative":[39],"conventional":[41,208],"hybrid":[42],"paradigms":[43],"with":[44,71,211,239],"deep":[45],"networks":[47],"and":[48,68,76,145,158,191],"hidden":[49],"Markov":[50],"models.":[51],"Using":[52],"this":[53],"novel":[54],"paradigm,":[55],"we":[56,123],"simplify":[57],"by":[60],"integrating":[61],"components":[64,80,147],"acoustic,":[66],"phonetic,":[67],"language":[69],"models":[70],"single":[73],"network":[75],"optimize":[77],"overall":[79],"objective:":[85],"generating":[86],"correct":[88],"label":[89],"sequence.":[90],"Although":[91],"most":[92],"existing":[93],"frameworks":[95],"have":[96],"mainly":[97],"focused":[98],"on":[99,182],"in":[101,113,167,187,220],"clean":[102],"environments,":[103],"our":[104,179,198,232],"aim":[105],"is":[106,236],"build":[108],"more":[109],"realistic":[110],"systems":[112],"noisy":[114,120,188],"environments.":[115],"To":[116],"handle":[117],"challenging":[119],"tasks,":[122],"study":[124],"multichannel":[125,132,184,200],"architecture,":[128],"which":[129,235],"directly":[130],"converts":[131],"text":[136],"through":[137],"enhancement.":[139],"allows":[142],"enhancement":[144],"be":[149],"jointly":[150],"optimized":[151,237],"improve":[153],"objective":[157],"leads":[159],"framework":[163],"that":[164,197,231],"works":[165],"well":[166],"presence":[169],"of":[170,178,222],"strong":[171],"background":[172],"noise.":[173],"We":[174],"elaborate":[175],"effectiveness":[177],"proposed":[180,199],"method":[181],"benchmarks":[186],"environments":[189],"(CHiME-4":[190],"AMI).":[192],"The":[193],"experimental":[194],"results":[195],"show":[196],"system":[202],"obtained":[203],"performance":[204],"gains":[205],"over":[206],"baseline":[210],"enhanced":[212],"inputs":[213],"from":[214],"delay-and-sum":[216],"(i.e.,":[218],"BeamformIT)":[219],"terms":[221],"character":[223],"error":[224],"rate.":[225],"In":[226],"addition,":[227],"further":[228],"analysis":[229],"shows":[230],"beamformer,":[234],"only":[238],"objective,":[243],"successfully":[244],"learned":[245],"noise":[247],"suppression":[248],"function.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}