{"id":"https://openalex.org/W3198134544","doi":"https://doi.org/10.21437/interspeech.2021-1190","title":"Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-Field Speech Recognition","display_name":"Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-Field Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198134544","doi":"https://doi.org/10.21437/interspeech.2021-1190","mag":"3198134544"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":null,"display_name":"Rong Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077676839","display_name":"Carl Quillen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carl Quillen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011337004","display_name":"Andrew Goderre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Goderre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011101212","display_name":"Jos\u00e9 Enrique Garc\u00eda La\u00ednez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 La\u00ednez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011519401","display_name":"Ljubomir Milanovi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ljubomir Milanovi\u0107","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6986,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84843007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.998199999332428,"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":0.9965999722480774,"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/combinatory-logic","display_name":"Combinatory logic","score":0.7807739973068237},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7442382574081421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6349580883979797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.580858051776886},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5434492230415344},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.458088755607605},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.3021571636199951},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2581263482570648},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14564526081085205}],"concepts":[{"id":"https://openalex.org/C79678938","wikidata":"https://www.wikidata.org/wiki/Q1481571","display_name":"Combinatory logic","level":2,"score":0.7807739973068237},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7442382574081421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6349580883979797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.580858051776886},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5434492230415344},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.458088755607605},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.3021571636199951},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2581263482570648},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14564526081085205},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2026765907","https://openalex.org/W4307413753","https://openalex.org/W1975604118","https://openalex.org/W119766800","https://openalex.org/W2313450777","https://openalex.org/W2162268423","https://openalex.org/W4242826518","https://openalex.org/W4236097997","https://openalex.org/W808564355","https://openalex.org/W4302028324"],"abstract_inverted_index":{"When":[0],"a":[1,11,88,98,103,112],"sufficiently":[2],"large":[3],"far-field":[4],"training":[5],"data":[6,92],"is":[7],"presented,":[8],"jointly":[9,109],"optimizing":[10],"multichannel":[12,77,89],"frontend":[13,49],"and":[14,124,128],"an":[15,51],"end-to-end":[16],"(E2E)":[17],"Automatic":[18],"Speech":[19],"Recognition":[20],"(ASR)":[21],"backend":[22],"shows":[23,93],"promising":[24],"results.":[25],"Recent":[26],"literature":[27],"has":[28],"shown":[29],"traditional":[30,126],"beamformer":[31],"designs,":[32],"such":[33],"as":[34,47],"MVDR":[35],"(Minimum":[36],"Variance":[37],"Distortionless":[38],"Response)":[39],"or":[40],"fixed":[41,105],"beamformers":[42],"can":[43],"be":[44],"successfully":[45],"integrated":[46],"the":[48,63,72,81,95,119,122,125,130,134],"into":[50],"E2E":[52],"ASR":[53,68,114],"system":[54],"with":[55,111],"learnable":[56],"parameters.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"propose":[62],"self-attention":[64,73],"channel":[65],"combinator":[66],"(SACC)":[67],"frontend,":[69,107],"which":[70],"leverages":[71],"mechanism":[74],"to":[75,102],"combine":[76],"audio":[78],"signals":[79],"in":[80],"magnitude":[82],"spectral":[83],"domain.":[84],"Experiments":[85],"conducted":[86],"on":[87],"playback":[90],"test":[91],"that":[94],"SACC":[96,123],"achieved":[97],"9.3%":[99],"WERR":[100],"compared":[101],"state-of-the-art":[104],"beamformer-based":[106],"both":[108],"optimized":[110],"ContextNet-based":[113],"backend.":[115],"We":[116],"also":[117],"demonstrate":[118],"connection":[120],"between":[121],"beamformers,":[127],"analyze":[129],"intermediate":[131],"outputs":[132],"of":[133],"SACC.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}