{"id":"https://openalex.org/W4393380070","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476930","title":"Distant, Multichannel Speech Recognition Using Microphone Array Coding and Cloud-Based Beamforming with a Self-Attention Channel Combinator","display_name":"Distant, Multichannel Speech Recognition Using Microphone Array Coding and Cloud-Based Beamforming with a Self-Attention Channel Combinator","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393380070","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476930"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10476930","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf59524.2023.10476930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-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/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Microsoft Inc.,USA","Microsoft Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Inc.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Inc., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110499","display_name":"Daniel T. Jones","orcid":"https://orcid.org/0000-0001-8095-1946"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Jones","raw_affiliation_strings":["Imperial College London,UK","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041925088","display_name":"Stanislav Yu. Kruchinin","orcid":"https://orcid.org/0000-0002-6495-3375"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanislav Kruchinin","raw_affiliation_strings":["Microsoft Inc.,Austria","Microsoft Inc., Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Inc.,Austria","institution_ids":[]},{"raw_affiliation_string":"Microsoft Inc., Austria","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":["Microsoft Inc.,Austria","Microsoft Inc., Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Inc.,Austria","institution_ids":[]},{"raw_affiliation_string":"Microsoft Inc., Austria","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London,UK","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22508357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1415","last_page":"1419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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":0.975600004196167,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.7032800912857056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6772651672363281},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6590295433998108},{"id":"https://openalex.org/keywords/combinatory-logic","display_name":"Combinatory logic","score":0.591298520565033},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5031279921531677},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.48896563053131104},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.47339141368865967},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4166979193687439},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20833584666252136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06291234493255615}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032800912857056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772651672363281},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6590295433998108},{"id":"https://openalex.org/C79678938","wikidata":"https://www.wikidata.org/wiki/Q1481571","display_name":"Combinatory logic","level":2,"score":0.591298520565033},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5031279921531677},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.48896563053131104},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.47339141368865967},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4166979193687439},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20833584666252136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06291234493255615},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10476930","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf59524.2023.10476930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","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":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983812858","https://openalex.org/W2046317813","https://openalex.org/W2117678320","https://openalex.org/W2143643945","https://openalex.org/W2155638623","https://openalex.org/W2164588373","https://openalex.org/W2286474545","https://openalex.org/W2398042854","https://openalex.org/W2506203739","https://openalex.org/W2803583024","https://openalex.org/W2921496354","https://openalex.org/W2936774411","https://openalex.org/W3003448205","https://openalex.org/W3086154751","https://openalex.org/W3095173472","https://openalex.org/W3126648213","https://openalex.org/W3197480135","https://openalex.org/W3198134544","https://openalex.org/W3212886388","https://openalex.org/W4200519813","https://openalex.org/W4226279385","https://openalex.org/W4246447287","https://openalex.org/W4297752165","https://openalex.org/W4312246529","https://openalex.org/W4312979902","https://openalex.org/W6630442970","https://openalex.org/W6773242556"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188"],"abstract_inverted_index":{"Distant":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"holds":[5],"the":[6,43,47,70,74,82,109,113,120,124,137,142,162,181],"promise":[7],"of":[8,28,49,76,108,126,136,144,180],"more":[9,195],"natural":[10],"human-machine":[11],"interface":[12],"and":[13,45,65,98,159,193],"using":[14],"multiple":[15],"microphones":[16],"to":[17,25,41,79,170,189],"acquire":[18],"speech":[19,44,89,101],"in":[20,69,119,173],"such":[21],"environments":[22],"often":[23],"leads":[24,169,188],"better":[26],"accuracy":[27],"ASR.":[29],"The":[30],"benefits":[31],"come":[32],"from":[33],"encoding":[34],"spatial":[35,114],"information":[36,115],"which":[37,72],"can":[38,116],"be":[39,117],"used":[40],"enhance":[42],"estimate":[46],"direction":[48],"sound":[50],"arrival.":[51],"Current":[52],"ASR":[53,158],"systems":[54],"are":[55,66],"based":[56,150],"on":[57],"end-to-end":[58],"models":[59],"that":[60,112,161,178],"require":[61],"considerable":[62],"computational":[63],"resources":[64],"typically":[67],"deployed":[68],"cloud,":[71],"requires":[73],"use":[75,125,143],"a":[77,87,127,145,185,190],"CODEC":[78],"help":[80],"reduce":[81],"transmission":[83],"bandwidth.":[84],"We":[85,122,139],"present":[86],"multichannel":[88],"coding":[90],"scheme":[91,104],"specifically":[92],"adapted":[93],"for":[94,157],"microphone":[95],"array":[96,182],"signals":[97,110,183],"unlike":[99],"typical":[100],"codecs,":[102],"this":[103],"preserves":[105],"phase":[106],"relationships":[107],"so":[111],"exploited":[118],"cloud.":[121],"explore":[123,141],"frequency":[128],"domain":[129,164],"relative":[130],"transfer":[131],"function":[132],"estimator":[133],"as":[134],"part":[135],"CODEC.":[138],"also":[140,194],"modified":[146],"discrete":[147],"cosine":[148],"transform":[149],"Self":[151],"Attention":[152],"Channel":[153],"Combinator":[154],"(SACC)":[155],"front-end":[156],"show":[160,177],"time":[163],"signal":[165],"post":[166],"SACC":[167],"processing":[168],"significant":[171],"improvements":[172],"C50.":[174],"Furthermore,":[175],"we":[176],"preprocessing":[179],"with":[184],"de-reverberation":[186],"method":[187],"lower":[191],"WER":[192],"accurate":[196],"DOA":[197],"estimation.":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
