{"id":"https://openalex.org/W2892163332","doi":"https://doi.org/10.1109/icassp.2018.8461639","title":"Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation","display_name":"Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892163332","doi":"https://doi.org/10.1109/icassp.2018.8461639","mag":"2892163332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","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":"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 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/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 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":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":267,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7988194227218628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408047914505005},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6271741986274719},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6016756296157837},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5817148089408875},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5649980306625366},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5635970234870911},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5506059527397156},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5323517918586731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141539573669434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5120628476142883},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5113000869750977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5063663721084595},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.47840771079063416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15590721368789673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12381783127784729},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07708868384361267}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7988194227218628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408047914505005},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6271741986274719},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6016756296157837},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5817148089408875},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5649980306625366},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5635970234870911},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5506059527397156},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5323517918586731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141539573669434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5120628476142883},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5113000869750977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5063663721084595},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.47840771079063416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15590721368789673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12381783127784729},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07708868384361267},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W123936940","https://openalex.org/W141203745","https://openalex.org/W1544785557","https://openalex.org/W1555217905","https://openalex.org/W1982172017","https://openalex.org/W1992879732","https://openalex.org/W2079362249","https://openalex.org/W2117678320","https://openalex.org/W2129116669","https://openalex.org/W2129171989","https://openalex.org/W2158143227","https://openalex.org/W2166458192","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2558649592","https://openalex.org/W2559809918","https://openalex.org/W2561557072","https://openalex.org/W2568308529","https://openalex.org/W2575498233","https://openalex.org/W2599685671","https://openalex.org/W2604869594","https://openalex.org/W2702006285","https://openalex.org/W2718052359","https://openalex.org/W2735663686","https://openalex.org/W2750380122","https://openalex.org/W2750446090","https://openalex.org/W2891405874","https://openalex.org/W2891984996","https://openalex.org/W2962715207","https://openalex.org/W3124972797","https://openalex.org/W3139695047","https://openalex.org/W4233392025","https://openalex.org/W6679489070","https://openalex.org/W6731182777"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W3119734852","https://openalex.org/W2011776247"],"abstract_inverted_index":{"The":[0],"recently-proposed":[1],"deep":[2,44,76],"clustering":[3,45,77],"algorithm":[4,107],"represents":[5],"a":[6,43,79,93],"fundamental":[7],"advance":[8],"towards":[9],"solving":[10],"the":[11,16,49,97,101,105],"cocktail":[12],"party":[13],"problem":[14],"in":[15,42,82,111],"single-channel":[17],"case.":[18],"When":[19],"multiple":[20],"microphones":[21],"are":[22],"available,":[23],"spatial":[24,40,53],"information":[25,54],"can":[26,55],"be":[27,56],"leveraged":[28],"to":[29,59],"differentiate":[30],"signals":[31],"from":[32],"different":[33],"directions.":[34],"This":[35],"study":[36],"combines":[37],"spectral":[38,51],"and":[39,52],"features":[41,74],"framework":[46],"so":[47],"that":[48,65],"complementary":[50],"simultaneously":[57],"exploited":[58],"improve":[60],"speech":[61,109],"separation.":[62],"We":[63],"find":[64],"simply":[66],"encoding":[67],"inter-microphone":[68],"phase":[69],"patterns":[70],"as":[71],"additional":[72],"input":[73],"during":[75],"provides":[78],"significant":[80],"improvement":[81],"separation":[83,110],"performance,":[84],"even":[85],"with":[86],"random":[87],"microphone":[88],"array":[89],"geometry.":[90],"Experiments":[91],"on":[92],"spatial-ized":[94],"version":[95],"of":[96,104],"wsj0-2mix":[98],"dataset":[99],"show":[100],"strong":[102],"potential":[103],"proposed":[106],"for":[108],"reverberant":[112],"environments.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":35},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":73},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}