{"id":"https://openalex.org/W3160207687","doi":"https://doi.org/10.1109/icassp39728.2021.9414123","title":"End-to-End Multi-Channel Transformer for Speech Recognition","display_name":"End-to-End Multi-Channel Transformer for Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160207687","doi":"https://doi.org/10.1109/icassp39728.2021.9414123","mag":"3160207687"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5102963746","display_name":"Feng-Ju Chang","orcid":"https://orcid.org/0000-0003-2405-3118"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng-Ju Chang","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Radfar","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Athanasios Mouchtaris","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027102522","display_name":"Brian King","orcid":"https://orcid.org/0000-0002-5300-5564"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian King","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siegfried Kunzmann","raw_affiliation_strings":["Alexa Machine Learning, Amazon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5884","last_page":"5888"},"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":0.9994000196456909,"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":0.6954060792922974},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6939189434051514},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5430753231048584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5325231552124023},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.49916744232177734},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4754825830459595},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4696333408355713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42840084433555603},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41519683599472046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3566904067993164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3435955047607422},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18761754035949707},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17285102605819702},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.17058825492858887},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16297823190689087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6954060792922974},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6939189434051514},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5430753231048584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5325231552124023},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49916744232177734},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4754825830459595},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4696333408355713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42840084433555603},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41519683599472046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3566904067993164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3435955047607422},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18761754035949707},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17285102605819702},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17058825492858887},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16297823190689087},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W81726370","https://openalex.org/W102482883","https://openalex.org/W1522301498","https://openalex.org/W1982728343","https://openalex.org/W2057035781","https://openalex.org/W2066218102","https://openalex.org/W2129227482","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2490695385","https://openalex.org/W2506203739","https://openalex.org/W2517616541","https://openalex.org/W2636483419","https://openalex.org/W2892009249","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2929050606","https://openalex.org/W2954695182","https://openalex.org/W2962784628","https://openalex.org/W2962970794","https://openalex.org/W2963399332","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2981857663","https://openalex.org/W3008762051","https://openalex.org/W3015791598","https://openalex.org/W3015834770","https://openalex.org/W3023895054","https://openalex.org/W3027687786","https://openalex.org/W3095552229","https://openalex.org/W3097973766","https://openalex.org/W4206633762","https://openalex.org/W4297801117","https://openalex.org/W4385245566","https://openalex.org/W6610836755","https://openalex.org/W6631190155","https://openalex.org/W6735168207","https://openalex.org/W6739901393","https://openalex.org/W6756579876","https://openalex.org/W6766224279","https://openalex.org/W6776359186","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W1974414866","https://openalex.org/W3016124757","https://openalex.org/W2275988210"],"abstract_inverted_index":{"Transformers":[0],"are":[1,37,90],"powerful":[2],"neural":[3,19,129],"architectures":[4,21],"that":[5,110],"allow":[6],"integrating":[7],"different":[8,35],"modalities":[9],"using":[10,39],"attention":[11,40,53,57,63],"mechanisms.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16],"leverage":[17],"the":[18,28,72,94,100,104,119,126,133],"transformer":[20,44],"for":[22],"multi-channel":[23,43,61],"speech":[24],"recognition":[25],"systems,":[26],"where":[27],"spectral":[29],"and":[30,60,68,76,79,88,128],"spatial":[31],"information":[32],"collected":[33],"from":[34,86],"microphones":[36],"integrated":[38],"layers.":[41],"Our":[42],"network":[45],"mainly":[46],"consists":[47],"of":[48],"three":[49],"parts:":[50],"channel-wise":[51],"self":[52],"layers":[54,58,64,70,96],"(CSA),":[55],"cross-channel":[56],"(CCA),":[59],"encoder-decoder":[62],"(EDA).":[65],"The":[66,83,107],"CSA":[67,87],"CCA":[69,89],"encode":[71],"contextual":[73],"relationship":[74],"\"within\"":[75],"\"between\"":[77],"channels":[78],"across":[80],"time,":[81],"respectively.":[82],"channel-attended":[84],"outputs":[85],"then":[91],"fed":[92],"into":[93],"EDA":[95],"to":[97],"help":[98],"decode":[99],"next":[101],"token":[102],"given":[103],"preceding":[105],"ones.":[106],"experiments":[108],"show":[109],"in":[111],"a":[112],"far-field":[113],"in-house":[114],"dataset,":[115],"our":[116],"method":[117],"outperforms":[118],"baseline":[120],"single-channel":[121],"transformer,":[122],"as":[123,125],"well":[124],"super-directive":[127],"beamformers":[130],"cascaded":[131],"with":[132],"transformers.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}