{"id":"https://openalex.org/W4226279385","doi":"https://doi.org/10.1109/icassp43922.2022.9746667","title":"Spatial Processing Front-End for Distant ASR Exploiting Self-Attention Channel Combinator","display_name":"Spatial Processing Front-End for Distant ASR Exploiting Self-Attention Channel Combinator","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226279385","doi":"https://doi.org/10.1109/icassp43922.2022.9746667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746667","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications Inc.,Research & Development,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,Research & Development,USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":["Nuance Communications GmbH,Research & Development,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications GmbH,Research & Development,Austria","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078802241","display_name":"James Fosburgh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Fosburgh","raw_affiliation_strings":["Nuance Communications Inc.,Research & Development,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,Research & Development,USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041925088","display_name":"Stanislav Yu. Kruchinin","orcid":"https://orcid.org/0000-0002-6495-3375"},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Stanislav Yu. Kruchinin","raw_affiliation_strings":["Nuance Communications GmbH,Research & Development,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications GmbH,Research & Development,Austria","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","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,Electronic & Electrical Engineering,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,Electronic & Electrical Engineering,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011519401","display_name":"Ljubomir Milanovi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ljubomir Milanovic","raw_affiliation_strings":["Nuance Communications GmbH,Research & Development,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications GmbH,Research & Development,Austria","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7262,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69058861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7997","last_page":"8001"},"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":0.9998000264167786,"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":0.9979000091552734,"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/channel","display_name":"Channel (broadcasting)","score":0.7484645247459412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012053728103638},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.6646338701248169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.572097897529602},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43449270725250244},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42331019043922424},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.41882458329200745},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3251676559448242},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2229863703250885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1517491638660431},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10405823588371277}],"concepts":[{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7484645247459412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012053728103638},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.6646338701248169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.572097897529602},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43449270725250244},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42331019043922424},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.41882458329200745},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3251676559448242},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2229863703250885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1517491638660431},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10405823588371277},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/icassp43922.2022.9746667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746667","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983812858","https://openalex.org/W2164502538","https://openalex.org/W2166547995","https://openalex.org/W2398042854","https://openalex.org/W2506203739","https://openalex.org/W2539797148","https://openalex.org/W2767071179","https://openalex.org/W2803583024","https://openalex.org/W2921496354","https://openalex.org/W2954695182","https://openalex.org/W2963197115","https://openalex.org/W3086154751","https://openalex.org/W3093726211","https://openalex.org/W3095173472","https://openalex.org/W3117722298","https://openalex.org/W3198134544","https://openalex.org/W6728770099","https://openalex.org/W6735168207","https://openalex.org/W6766380642","https://openalex.org/W6787857153"],"related_works":["https://openalex.org/W2532234348","https://openalex.org/W108084911","https://openalex.org/W2393440248","https://openalex.org/W2673314300","https://openalex.org/W1569386110","https://openalex.org/W2720892868","https://openalex.org/W2982169251","https://openalex.org/W2103406007","https://openalex.org/W2252127188","https://openalex.org/W2126436624"],"abstract_inverted_index":{"We":[0,41,77,125],"present":[1],"a":[2,19,27,51,65,72,93],"novel":[3],"multi-channel":[4,73],"front-end":[5],"based":[6,53],"on":[7,71],"channel":[8,31,96,113],"shortening":[9,97],"with":[10,26,92],"the":[11,37,44,89,102,106,111,120,129,132,136],"Weighted":[12],"Prediction":[13],"Error":[14],"(WPE)":[15],"method":[16,91,115],"followed":[17],"by":[18,64],"fixed":[20],"MVDR":[21],"beamformer":[22],"used":[23,47],"in":[24,68],"combination":[25,32],"recently":[28],"proposed":[29,45],"self-attention-based":[30],"(SACC)":[33],"scheme,":[34],"for":[35,146],"tackling":[36],"distant":[38],"ASR":[39,56,60],"problem.":[40],"show":[42,79,127],"that":[43,110],"system":[46,57,134],"as":[48,62],"part":[49],"of":[50,101,105,119,131,138],"ContextNet":[52],"end-to-end":[54],"(E2E)":[55],"outperforms":[58],"leading":[59],"systems":[61],"demonstrated":[63],"21.6%":[66],"reduction":[67],"relative":[69],"WER":[70],"LibriSpeech":[74],"playback":[75],"dataset.":[76],"also":[78,126],"how":[80,128],"dereverberation":[81,118],"prior":[82],"to":[83],"beam-forming":[84],"is":[85],"beneficial":[86,145],"and":[87],"compare":[88],"WPE":[90,114],"modified":[94],"neural":[95],"approach.":[98],"An":[99],"analysis":[100],"non-intrusive":[103],"estimate":[104],"signal":[107],"C50":[108],"confirms":[109],"8":[112],"provides":[116],"significant":[117],"signals":[121],"(13.6":[122],"dB":[123],"improvement).":[124],"weights":[130],"SACC":[133],"allow":[135],"extraction":[137],"accurate":[139],"spatial":[140],"information":[141],"which":[142],"can":[143],"be":[144],"other":[147],"speech":[148],"processing":[149],"applications":[150],"like":[151],"diarization.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}