{"id":"https://openalex.org/W2936302822","doi":"https://doi.org/10.1109/icassp.2019.8683448","title":"A Unified Framework for Neural Speech Separation and Extraction","display_name":"A Unified Framework for Neural Speech Separation and Extraction","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936302822","doi":"https://doi.org/10.1109/icassp.2019.8683448","mag":"2936302822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"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":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6975","last_page":"6979"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.7869199514389038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.705765962600708},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5934730768203735},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5440186858177185},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5108551383018494},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.471529096364975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4537643492221832},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.44547605514526367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4408129155635834},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.43784698843955994},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43387627601623535},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.34758082032203674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18383759260177612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869199514389038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.705765962600708},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5934730768203735},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5440186858177185},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5108551383018494},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.471529096364975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4537643492221832},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.44547605514526367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408129155635834},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.43784698843955994},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43387627601623535},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.34758082032203674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18383759260177612},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1815076433","https://openalex.org/W2127851351","https://openalex.org/W2133564696","https://openalex.org/W2157906748","https://openalex.org/W2160815625","https://openalex.org/W2221409856","https://openalex.org/W2398776621","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2787692317","https://openalex.org/W2801839390","https://openalex.org/W2884797218","https://openalex.org/W2891054259","https://openalex.org/W2891833136","https://openalex.org/W2913340405","https://openalex.org/W2916979304","https://openalex.org/W2939771864","https://openalex.org/W2962780374","https://openalex.org/W2964121744","https://openalex.org/W2964238697","https://openalex.org/W2964308564","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W2390344110","https://openalex.org/W2364896863","https://openalex.org/W2361066326","https://openalex.org/W2046761971","https://openalex.org/W2107364365","https://openalex.org/W2118307209","https://openalex.org/W1785857632","https://openalex.org/W4281722104","https://openalex.org/W2187523794","https://openalex.org/W1503525627"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,11,114],"deep":[3],"learning":[4],"techniques":[5],"has":[6],"triggered":[7],"the":[8,50,74,88,105,161,165],"active":[9],"investigation":[10],"neural":[12],"network-based":[13],"speech":[14,22,27,34,38,55,60,101,124,127,150],"enhancement":[15],"approaches.":[16],"In":[17,52,108],"particular,":[18],"single-channel":[19],"blind":[20,94,149],"(uninformed)":[21],"separation":[23,35,125,151,176],"and":[24,97,126,153,177,180],"speaker-aware":[25,54],"(informed)":[26],"extraction":[28,56,78,128],"have":[29],"received":[30],"increased":[31],"interest.":[32],"Blind":[33],"separates":[36],"a":[37,62,119,130,138,143,155,186],"mixture":[39],"into":[40],"all":[41],"source":[42,89,95],"signals":[43],"without":[44],"requiring":[45],"any":[46],"auxiliary":[47,106],"information":[48],"about":[49],"speakers.":[51],"contrast,":[53],"focuses":[57],"on":[58,164],"extracting":[59],"from":[61],"target":[63,75],"speaker":[64,139],"using":[65,129],"prior":[66],"knowledge,":[67],"such":[68],"as":[69],"an":[70],"utterance":[71],"spoken":[72],"by":[73,93,103,136],"speaker.":[76],"Speaker":[77],"is":[79,134],"therefore":[80],"not":[81],"fully":[82],"blind,":[83],"but":[84],"it":[85],"can":[86],"mitigate":[87],"permutation":[90,145],"problem":[91],"faced":[92],"separation,":[96],"potentially":[98],"achieve":[99],"better":[100,182],"quality":[102],"exploiting":[104],"information.":[107],"this":[109],"paper,":[110],"to":[111],"take":[112],"advantage":[113],"both":[115,123,174],"approaches,":[116],"we":[117],"propose":[118],"unified":[120],"framework":[121,172],"for":[122,159],"single":[131],"model.":[132,162,189],"This":[133],"realized":[135],"incorporating":[137],"attention":[140],"mechanism":[141],"within":[142],"generalized":[144],"invariant":[146],"training":[147,160],"(PIT)-based":[148],"model,":[152],"introducing":[154],"multitask":[156],"separation/extraction":[157,183],"objective":[158],"Experiments":[163],"WSJ0-2mix":[166],"dataset":[167],"show":[168],"that":[169],"our":[170],"proposed":[171],"realizes":[173],"uninformed":[175],"informed":[178],"extraction,":[179],"achieves":[181],"performance":[184],"than":[185],"baseline":[187],"PIT-based":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}