{"id":"https://openalex.org/W3008742825","doi":"https://doi.org/10.1109/icassp40776.2020.9054721","title":"An Empirical Study of Conv-Tasnet","display_name":"An Empirical Study of Conv-Tasnet","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3008742825","doi":"https://doi.org/10.1109/icassp40776.2020.9054721","mag":"3008742825"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054721","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.08688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015636322","display_name":"Berkan Kad\u0131o\u011flu","orcid":"https://orcid.org/0000-0002-1261-3758"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Berkan Kadioglu","raw_affiliation_strings":["Northeastern University,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066237118","display_name":"Michael A. Horgan","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["NL","SE"],"is_corresponding":false,"raw_author_name":"Michael Horgan","raw_affiliation_strings":["Dolby Laboratories","Dolby Labs"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Dolby Labs","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455531","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0005-6402-3855"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["NL","SE"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Dolby Laboratories","Dolby Labs"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Dolby Labs","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["NL","SE"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Dolby Laboratories","Dolby Labs"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Dolby Labs","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006885909","display_name":"Dan Darcy","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["NL","SE"],"is_corresponding":false,"raw_author_name":"Dan Darcy","raw_affiliation_strings":["Dolby Laboratories","Dolby Labs"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Dolby Labs","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060822647","display_name":"Vivek Kumar","orcid":"https://orcid.org/0000-0002-0083-5839"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["NL","SE"],"is_corresponding":false,"raw_author_name":"Vivek Kumar","raw_affiliation_strings":["Dolby Laboratories","Dolby Labs"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Dolby Labs","institution_ids":["https://openalex.org/I4210093833"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015636322"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01968607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7264","last_page":"7268"},"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":0.9997000098228455,"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":0.9994999766349792,"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/encoder","display_name":"Encoder","score":0.787468671798706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720186114311218},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5993481874465942},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49142754077911377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4890230596065521},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4631229341030121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119688868522644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3838370442390442},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.357124924659729},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14766591787338257}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.787468671798706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720186114311218},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5993481874465942},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49142754077911377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4890230596065521},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4631229341030121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119688868522644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3838370442390442},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.357124924659729},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14766591787338257},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054721","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"},{"id":"pmh:oai:arXiv.org:2002.08688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08688","pdf_url":"https://arxiv.org/pdf/2002.08688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2002.08688","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.08688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/rwce-vd46","is_oa":true,"landing_page_url":"https://doi.org/10.17023/rwce-vd46","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3008742825","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.08688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08688","pdf_url":"https://arxiv.org/pdf/2002.08688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008742825.pdf","grobid_xml":"https://content.openalex.org/works/W3008742825.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1607274768","https://openalex.org/W2029654180","https://openalex.org/W2120847449","https://openalex.org/W2221409856","https://openalex.org/W2510642588","https://openalex.org/W2527729766","https://openalex.org/W2734774145","https://openalex.org/W2891355459","https://openalex.org/W2894785362","https://openalex.org/W2898963093","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2944972166","https://openalex.org/W2949382160","https://openalex.org/W2952218014","https://openalex.org/W2962813390","https://openalex.org/W2963103134","https://openalex.org/W2963232038","https://openalex.org/W2963519193","https://openalex.org/W2963723765","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W2972460025","https://openalex.org/W2972653970","https://openalex.org/W2972693890","https://openalex.org/W2972853597","https://openalex.org/W2973054567","https://openalex.org/W2973143779","https://openalex.org/W3028311979","https://openalex.org/W6734751391","https://openalex.org/W6745878906","https://openalex.org/W6751512325","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3015700067","https://openalex.org/W3151066410","https://openalex.org/W3096675975","https://openalex.org/W3176696796","https://openalex.org/W3165858867","https://openalex.org/W3135456353","https://openalex.org/W2973212992","https://openalex.org/W3098276096","https://openalex.org/W2945588488","https://openalex.org/W3103860344","https://openalex.org/W3014802836","https://openalex.org/W3125875312","https://openalex.org/W3174379936","https://openalex.org/W2926063217","https://openalex.org/W2810169681","https://openalex.org/W3119635310","https://openalex.org/W2949185934","https://openalex.org/W2992441690","https://openalex.org/W2948522988","https://openalex.org/W1626973579"],"abstract_inverted_index":{"Conv-TasNet":[0,66,154],"is":[1,75],"a":[2,21,25,53,78,108],"recently":[3],"proposed":[4,39],"waveform-based":[5],"deep":[6],"neural":[7],"network":[8],"that":[9,27,74,116,130],"achieves":[10],"state-of-the-art":[11],"performance":[12,139],"in":[13],"speech":[14],"source":[15],"separation.":[16],"Its":[17],"architecture":[18],"consists":[19],"of":[20,31,65,82,101,153,159],"learnable":[22],"encoder/decoder":[23,51,73,134],"and":[24,67,91,96,124,155],"separator":[26],"operates":[28],"on":[29,46,77,107],"top":[30],"this":[32,58],"learned":[33],"space.":[34],"Various":[35],"improvements":[36,160],"have":[37],"been":[38],"to":[40,71,132,161],"Conv-TasNet.":[41],"However,":[42],"they":[43],"mostly":[44],"focus":[45],"the":[47,72,89,98,102,121,133,150,156,162],"separator,":[48],"leaving":[49],"its":[50],"as":[52],"(shallow)":[54],"linear":[55],"operator.":[56],"In":[57,84],"paper,":[59],"we":[60,86,146],"conduct":[61],"an":[62,69],"empirical":[63],"study":[64],"propose":[68,113],"enhancement":[70],"based":[76],"(deep)":[79],"non-linear":[80],"variant":[81],"it.":[83],"addition,":[85],"experiment":[87],"with":[88],"larger":[90,110],"more":[92,141],"diverse":[93],"LibriTTS":[94,123],"dataset":[95],"investigate":[97],"generalization":[99,151],"capabilities":[100,152],"studied":[103],"models":[104],"when":[105],"trained":[106],"much":[109],"dataset.":[111],"We":[112],"cross-dataset":[114],"evaluation":[115],"includes":[117],"assessing":[118],"separations":[119],"from":[120],"WSJ0-2mix,":[122],"VCTK":[125],"databases.":[126],"Our":[127],"results":[128],"show":[129],"enhancements":[131],"can":[135],"improve":[136],"average":[137],"SI-SNR":[138],"by":[140],"than":[142],"1":[143],"dB.":[144],"Furthermore,":[145],"offer":[147],"insights":[148],"into":[149],"potential":[157],"value":[158],"encoder/decoder.":[163]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2020-03-06T00:00:00"}