{"id":"https://openalex.org/W3213096249","doi":"https://doi.org/10.48550/arxiv.2111.04312","title":"Inter-channel Conv-TasNet for multichannel speech enhancement","display_name":"Inter-channel Conv-TasNet for multichannel speech enhancement","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3213096249","doi":"https://doi.org/10.48550/arxiv.2111.04312","mag":"3213096249"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2111.04312","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.04312","pdf_url":"https://arxiv.org/pdf/2111.04312","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.04312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100436257","display_name":"Dongheon Lee","orcid":"https://orcid.org/0000-0002-3121-7099","observed_orcids":["https://orcid.org/0000-0002-3121-7099"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lee, Dongheon","raw_affiliation_strings":["School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012028344","display_name":"Seongrae Kim","orcid":"https://orcid.org/0009-0004-7344-2122","observed_orcids":["https://orcid.org/0009-0004-7344-2122"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Seongrae","raw_affiliation_strings":["School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002212089","display_name":"Jung\u2010Woo Choi","orcid":"https://orcid.org/0000-0002-7264-6017","observed_orcids":["https://orcid.org/0000-0002-7264-6017"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Jung-Woo","raw_affiliation_strings":["School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering , Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141 , South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multichannel-speech-enhancement","display_name":"multichannel speech enhancement","score":0.9890000224113464},{"id":"https://openalex.org/keywords/conv-tasnet","display_name":"Conv-TasNet","score":0.972000002861023},{"id":"https://openalex.org/keywords/spatial-data","display_name":"geospatial data","score":0.6790000200271606},{"id":"https://openalex.org/keywords/3d-convolution","display_name":"3D convolution","score":0.6349999904632568},{"id":"https://openalex.org/keywords/microphone-array","display_name":"microphone array","score":0.5049999952316284},{"id":"https://openalex.org/keywords/chime-3","display_name":"CHiME-3","score":0.7129999995231628},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.812648594379425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290816307067871},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6357194781303406},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6252294182777405},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5822173357009888},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5453675389289856},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49688461422920227},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48805201053619385},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4352354407310486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42998629808425903},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39845171570777893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36537885665893555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3554927706718445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3212493062019348},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11340302228927612},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08970043063163757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2111.04312","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.04312","pdf_url":"https://arxiv.org/pdf/2111.04312","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3213096249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2111.04312.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.04312","doi":"https://doi.org/10.48550/arxiv.2111.04312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.04312","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.04312","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.04312","pdf_url":"https://arxiv.org/pdf/2111.04312","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213096249.pdf","grobid_xml":"https://content.openalex.org/works/W3213096249.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1963970749","https://openalex.org/W1990055747","https://openalex.org/W2044893557","https://openalex.org/W2075107327","https://openalex.org/W2078528584","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2147455188","https://openalex.org/W2289394825","https://openalex.org/W2290505958","https://openalex.org/W2291877678","https://openalex.org/W2398042854","https://openalex.org/W2405774341","https://openalex.org/W2510642588","https://openalex.org/W2517616541","https://openalex.org/W2526733715","https://openalex.org/W2531409750","https://openalex.org/W2550143307","https://openalex.org/W2561557072","https://openalex.org/W2612445135","https://openalex.org/W2614024025","https://openalex.org/W2626544737","https://openalex.org/W2792643794","https://openalex.org/W2809824582","https://openalex.org/W2889442120","https://openalex.org/W2923728956","https://openalex.org/W2937581095","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W2972754898","https://openalex.org/W3003441391","https://openalex.org/W3016257794","https://openalex.org/W3027637851","https://openalex.org/W3095166612","https://openalex.org/W3145315827"],"related_works":["https://openalex.org/W4320182977","https://openalex.org/W4410415533","https://openalex.org/W3181007310","https://openalex.org/W4296450727","https://openalex.org/W7000275337","https://openalex.org/W4319862664","https://openalex.org/W2589857635","https://openalex.org/W4220936942","https://openalex.org/W4386907436","https://openalex.org/W2766930522"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,60],"in":[2,14,27,47,181,225],"multichannel":[3,35,105,196],"settings":[4],"has":[5],"been":[6,24],"realized":[7],"by":[8],"utilizing":[9],"the":[10,33,65,117,121,145,153,160,169,174,194,211,217],"spatial":[11,40,131,163],"information":[12,41,172],"embedded":[13],"multiple":[15],"microphone":[16],"signals.":[17],"Moreover,":[18],"deep":[19],"neural":[20,199],"networks":[21],"(DNNs)":[22],"have":[23],"recently":[25],"advanced":[26],"this":[28,52,113],"field;":[29],"however,":[30],"studies":[31],"on":[32,81,144],"efficient":[34],"network":[36,61,88,122,176],"structure":[37,147],"fully":[38,83],"exploiting":[39],"and":[42,108,134,148,155,162,228],"inter-channel":[43,68,110,171,191],"relationships":[44,69],"is":[45,79,214],"still":[46],"its":[48],"early":[49],"stages.":[50],"In":[51,137],"study,":[53],"we":[54,115,139],"propose":[55,149],"an":[56],"end-to-end":[57],"time-domain":[58,85],"speech":[59,93],"that":[62,102,168],"can":[63,103],"facilitate":[64],"use":[66],"of":[67,73,120,152,198,204,210],"at":[70],"individual":[71],"layers":[72,158],"a":[74,82,178,222],"DNN.":[75],"The":[76,189,208],"proposed":[77,175,190,212],"technique":[78],"based":[80],"convolutional":[84],"audio":[86],"separation":[87,94],"(Conv-TasNet),":[89],"originally":[90],"developed":[91],"for":[92],"tasks.":[95],"We":[96,166],"extend":[97],"Conv-TasNet":[98,192],"into":[99],"several":[100],"forms":[101],"handle":[104],"input":[106],"signals":[107,184],"learn":[109],"relationships.":[111],"To":[112],"end,":[114],"modify":[116],"encoder-mask-decoder":[118],"structures":[119],"to":[123,159],"be":[124],"compatible":[125],"with":[126,202],"3-D":[127],"tensors":[128],"defined":[129],"over":[130],"channels,":[132],"features,":[133],"time":[135],"dimensions.":[136],"particular,":[138],"conduct":[140],"extensive":[141],"parameter":[142,206],"analyses":[143],"convolution":[146,157],"independent":[150],"assignment":[151],"depthwise":[154],"1$\\times$1":[156],"feature":[161],"dimensions,":[164],"respectively.":[165],"demonstrate":[167],"enriched":[170],"from":[173,186],"plays":[177],"significant":[179],"role":[180],"suppressing":[182],"noisy":[183],"impinging":[185],"various":[187],"directions.":[188],"outperforms":[193],"state-of-the-art":[195],"variants":[197],"networks,":[200],"even":[201],"one-tenth":[203],"their":[205],"size.":[207],"performance":[209],"model":[213],"evaluated":[215],"using":[216],"CHiME-3":[218],"dataset,":[219],"which":[220],"exhibits":[221],"remarkable":[223],"improvement":[224],"SDR,":[226],"PESQ,":[227],"STOI.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-22T00:00:00"}