{"id":"https://openalex.org/W2465050681","doi":"https://doi.org/10.21437/interspeech.2016-1176","title":"Single-Channel Multi-Speaker Separation Using Deep Clustering","display_name":"Single-Channel Multi-Speaker Separation Using Deep Clustering","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2465050681","doi":"https://doi.org/10.21437/interspeech.2016-1176","mag":"2465050681"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1176","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1607.02173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032821223","display_name":"Yusuf Ziya I\u015f\u0131k","orcid":"https://orcid.org/0000-0002-2002-7900"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["TR","US"],"is_corresponding":false,"raw_author_name":"Yusuf Isik","raw_affiliation_strings":["Mitsubishi Electric Research USA","Sabanci University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Sabanci University","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620750","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-0661-3628"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Mitsubishi Electric Research USA","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"549"},"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":0.9988999962806702,"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":0.9986000061035156,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7922153472900391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792155742645264},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6185043454170227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6175997853279114},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5213112235069275},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5079639554023743},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5051618218421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4955533742904663},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4647599458694458},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4594275951385498},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4586607813835144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4455142319202423},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44443032145500183},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43034815788269043},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.42510056495666504},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41734522581100464},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4162612557411194},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4108721613883972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2548934817314148},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19112175703048706}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7922153472900391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792155742645264},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6185043454170227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6175997853279114},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5213112235069275},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5079639554023743},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5051618218421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4955533742904663},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4647599458694458},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4594275951385498},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4586607813835144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4455142319202423},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44443032145500183},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43034815788269043},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.42510056495666504},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41734522581100464},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4162612557411194},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4108721613883972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2548934817314148},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19112175703048706},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2016-1176","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1607.02173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.02173","pdf_url":"https://arxiv.org/pdf/1607.02173","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":"mag:2465050681","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1607.02173.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1607.02173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1607.02173","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1607.02173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.02173","pdf_url":"https://arxiv.org/pdf/1607.02173","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":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2465050681.pdf","grobid_xml":"https://content.openalex.org/works/W2465050681.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W1482149378","https://openalex.org/W1513606575","https://openalex.org/W1524333225","https://openalex.org/W1550027367","https://openalex.org/W1591801644","https://openalex.org/W1790748249","https://openalex.org/W1831449718","https://openalex.org/W1964538581","https://openalex.org/W2008565517","https://openalex.org/W2060822897","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2088361146","https://openalex.org/W2113526703","https://openalex.org/W2124149378","https://openalex.org/W2129116669","https://openalex.org/W2147174722","https://openalex.org/W2221409856","https://openalex.org/W2292443655"],"related_works":["https://openalex.org/W2221409856","https://openalex.org/W2558649592","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2127851351","https://openalex.org/W2962935966","https://openalex.org/W2735663686","https://openalex.org/W2069681747","https://openalex.org/W2891405874","https://openalex.org/W2952218014","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W2962866211","https://openalex.org/W2799119527","https://openalex.org/W2552071709","https://openalex.org/W1494198834","https://openalex.org/W2291877678","https://openalex.org/W1552314771","https://openalex.org/W2315268655","https://openalex.org/W2144763279"],"abstract_inverted_index":{"Deep":[0],"clustering":[1,134],"is":[2],"a":[3,53,74,104,175],"recently":[4,21],"introduced":[5],"deep":[6],"learning":[7],"architecture":[8],"that":[9,48],"uses":[10],"discriminatively":[11],"trained":[12],"embeddings":[13],"as":[14,101,103],"the":[15,39,62,93,115,124,133,144,163,180],"basis":[16],"for":[17,98,109],"clustering.":[18],"It":[19],"was":[20],"applied":[22],"to":[23,84,92,117,122,138,171],"spectrogram":[24],"segmentation,":[25],"resulting":[26],"in":[27,78,82],"impressive":[28],"results":[29,145],"on":[30,52],"speaker-independent":[31],"multi-speaker":[32],"separation.":[33,56,111],"In":[34],"this":[35],"paper":[36],"we":[37],"extend":[38,114],"baseline":[40,63,94],"system":[41,64],"with":[42,156],"an":[43,79,119],"end-to-end":[44,129,157],"signal":[45,83,125,140,152],"approximation":[46,153],"objective":[47],"greatly":[49],"improves":[50],"performance":[51,65],"challenging":[54],"speech":[55,148],"We":[57,112,142],"first":[58],"significantly":[59],"improve":[60],"upon":[61],"by":[66],"incorporating":[67],"better":[68],"regularization,":[69],"larger":[70],"temporal":[71],"context,":[72],"and":[73,127,135],"deeper":[75],"architecture,":[76],"culminating":[77],"overall":[80],"improvement":[81,108],"distortion":[85],"ratio":[86],"(SDR)":[87],"of":[88,95],"10.3":[89],"dB":[90,97,106],"compared":[91],"6.0":[96],"two-speaker":[99],"separation,":[100],"well":[102],"7.1":[105],"SDR":[107],"three-speaker":[110],"then":[113],"model":[116],"incorporate":[118],"enhancement":[120,136],"layer":[121],"refine":[123],"estimates,":[126],"perform":[128],"training":[130],"through":[131],"both":[132],"stages":[137],"maximize":[139],"fidelity.":[141],"evaluate":[143],"using":[146],"automatic":[147],"recognition.":[149],"The":[150],"new":[151],"objective,":[154],"combined":[155],"training,":[158],"produces":[159],"unprecedented":[160],"performance,":[161],"reducing":[162],"word":[164],"error":[165],"rate":[166],"(WER)":[167],"from":[168],"89.1%":[169],"down":[170],"30.8%.":[172],"This":[173],"represents":[174],"major":[176],"advancement":[177],"towards":[178],"solving":[179],"cocktail":[181],"party":[182],"problem.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2016-07-22T00:00:00"}