{"id":"https://openalex.org/W2939518062","doi":"https://doi.org/10.1109/icassp.2019.8682695","title":"Teacher-student Deep Clustering for Low-delay Single Channel Speech Separation","display_name":"Teacher-student Deep Clustering for Low-delay Single Channel Speech Separation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939518062","doi":"https://doi.org/10.1109/icassp.2019.8682695","mag":"2939518062"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682695","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/A5011355805","display_name":"Ryo Aihara","orcid":"https://orcid.org/0009-0006-6492-3754"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Aihara","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112393630","display_name":"Toshiyuki Hanazawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiyuki Hanazawa","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003604821","display_name":"Yohei Okato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Okato","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"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":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","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 Laboratories (MERL), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"690","last_page":"694"},"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":0.9998000264167786,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058897852897644},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7754603624343872},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6569125652313232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5942592620849609},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.536631166934967},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5269466042518616},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5144848823547363},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.47035813331604004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44103533029556274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32393312454223633},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12607526779174805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058897852897644},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7754603624343872},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6569125652313232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5942592620849609},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.536631166934967},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5269466042518616},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5144848823547363},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.47035813331604004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44103533029556274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32393312454223633},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12607526779174805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682695","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":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W285277413","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1964538581","https://openalex.org/W2060822897","https://openalex.org/W2079362249","https://openalex.org/W2129116669","https://openalex.org/W2221409856","https://openalex.org/W2517616541","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2631415506","https://openalex.org/W2734774145","https://openalex.org/W2773624778","https://openalex.org/W2890111732","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2894785362","https://openalex.org/W2900132857","https://openalex.org/W2962715207","https://openalex.org/W2963773971","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W2964084166","https://openalex.org/W2964121744","https://openalex.org/W4256399001","https://openalex.org/W6603255414","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6679489070","https://openalex.org/W6736173540","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W3163341049","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W2885352820","https://openalex.org/W4296591952"],"abstract_inverted_index":{"The":[0],"recently-proposed":[1],"deep":[2,48],"clustering":[3,15,49],"algorithm":[4,34],"introduced":[5],"significant":[6],"advances":[7],"in":[8],"monaural":[9],"speaker-independent":[10],"multi-speaker":[11],"speech":[12,125],"separation.":[13],"Deep":[14],"operates":[16],"on":[17,106],"magnitude":[18],"spectro-grams":[19],"using":[20],"bidirectional":[21],"recurrent":[22,63],"networks":[23],"and":[24,65,96],"K-means":[25],"clustering,":[26],"both":[27],"of":[28,93,103,118,133],"which":[29],"require":[30],"offline":[31,75,82],"operation,":[32],"i.e.,":[33],"latency":[35,47,92,102],"is":[36,137],"longer":[37],"than":[38],"utterance":[39],"length.":[40],"This":[41],"paper":[42],"evaluates":[43],"architectures":[44],"for":[45,122],"reduced":[46],"by":[50,61,113],"combining:":[51],"(1)":[52],"block":[53],"processing":[54],"to":[55,78,139,147],"efficiently":[56],"propagate":[57],"the":[58,62,107,119,131,144],"memory":[59],"encoded":[60],"network,":[64],"(2)":[66],"teacher-student":[67],"learning,":[68],"where":[69,143],"low-latency":[70,124],"models":[71],"learn":[72],"from":[73],"an":[74,153],"teacher.":[76],"Compared":[77],"our":[79,123],"best":[80],"performing":[81],"model,":[83],"we":[84,128],"only":[85],"lose":[86],"0.3":[87],"dB":[88,98],"SDR":[89,99],"at":[90,100],"a":[91,101,115],"1.2":[94],"seconds":[95,105],"0.7":[97],"0.6":[104],"publicly":[108],"available":[109],"wsj0-2mix":[110],"dataset.":[111],"Moreover,":[112],"providing":[114],"detailed":[116],"analysis":[117],"failure":[120],"cases":[121],"separation":[126],"models,":[127],"show":[129],"that":[130],"cause":[132],"this":[134],"performance":[135],"gap":[136],"related":[138],"frame-level":[140],"permutation":[141],"errors,":[142],"network":[145],"fails":[146],"accurately":[148],"track":[149],"speaker":[150],"identity":[151],"throughout":[152],"utterance.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}