{"id":"https://openalex.org/W3015788098","doi":"https://doi.org/10.1109/icassp40776.2020.9053575","title":"Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer","display_name":"Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015788098","doi":"https://doi.org/10.1109/icassp40776.2020.9053575","mag":"3015788098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070624983"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":8.9405,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9875576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6384","last_page":"6388"},"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/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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7731982469558716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7552666664123535},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6190444827079773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6132774949073792},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5957500338554382},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.527379035949707},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4755370616912842},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.47241273522377014},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42699044942855835},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4248393177986145},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1826448142528534},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.0919986367225647}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7731982469558716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552666664123535},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6190444827079773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6132774949073792},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5957500338554382},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.527379035949707},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4755370616912842},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.47241273522377014},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42699044942855835},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4248393177986145},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1826448142528534},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.0919986367225647},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2050551142","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2514741789","https://openalex.org/W2517616541","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2884797218","https://openalex.org/W2892163332","https://openalex.org/W2892365986","https://openalex.org/W2916979304","https://openalex.org/W2935846637","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972693890","https://openalex.org/W3099330747","https://openalex.org/W6712626118","https://openalex.org/W6754743415","https://openalex.org/W6762182681"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2767070583","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2784052451","https://openalex.org/W2396048001","https://openalex.org/W2348931051"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,146],"acoustic":[5],"beamforming":[6,39,89,156],"using":[7],"a":[8,55,108,123,161],"microphone":[9],"array":[10],"plays":[11],"an":[12,167],"important":[13],"role":[14],"in":[15,42,95],"the":[16,35,43,47,63,81,119,141,152],"construction":[17],"of":[18,37,76,83],"high-performance":[19],"automatic":[20],"speech":[21,30,44,71,97,110],"recognition":[22],"(ASR)":[23],"systems,":[24],"especially":[25],"for":[26,40,66],"noisy":[27],"and":[28,60],"overlapping":[29,96],"conditions.":[31],"In":[32,74],"parallel":[33],"with":[34,118],"success":[36],"multichannel":[38],"ASR,":[41],"separation":[45,50,72,111],"field,":[46],"time-domain":[48,56,64],"audio":[49],"network":[51],"(TasNet),":[52],"which":[53,115],"accepts":[54],"mixture":[57],"as":[58],"input":[59],"directly":[61],"estimates":[62],"waveforms":[65],"each":[67],"source,":[68],"achieves":[69,160],"remarkable":[70],"performance.":[73,138],"light":[75],"these":[77],"two":[78],"recent":[79],"trends,":[80],"question":[82],"whether":[84],"TasNet":[85,117,154],"can":[86],"benefit":[87],"from":[88],"to":[90,134,166],"achieve":[91,135],"high":[92],"ASR":[93,137],"performance":[94],"conditions":[98],"naturally":[99],"arises.":[100],"Motivated":[101],"by":[102],"this":[103,105],"question,":[104],"paper":[106],"proposes":[107],"novel":[109],"scheme,":[112],"i.e.,":[113,122],"Beam-TasNet,":[114],"combines":[116],"frequency-domain":[120],"beamformer,":[121,129],"minimum":[124],"variance":[125],"distortionless":[126],"response":[127],"(MVDR)":[128],"through":[130],"spatial":[131],"covariance":[132],"computation":[133],"better":[136],"Experiments":[139],"on":[140],"spatialized":[142],"WSJ0-2mix":[143],"corpus":[144],"show":[145],"our":[147],"proposed":[148],"Beam-TasNet":[149],"significantly":[150],"outperforms":[151],"conventional":[153],"without":[155],"and,":[157],"moreover,":[158],"successfully":[159],"word":[162],"error":[163],"rate":[164],"comparable":[165],"oracle":[168],"mask-based":[169],"MVDR":[170],"beamformer.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}