{"id":"https://openalex.org/W3161301466","doi":"https://doi.org/10.1109/icassp39728.2021.9414205","title":"Multi-Decoder Dprnn: Source Separation for Variable Number of Speakers","display_name":"Multi-Decoder Dprnn: Source Separation for Variable Number of Speakers","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161301466","doi":"https://doi.org/10.1109/icassp39728.2021.9414205","mag":"3161301466"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5048524258","display_name":"Junzhe Zhu","orcid":"https://orcid.org/0000-0002-4316-8570"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhe Zhu","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076130922","display_name":"Raymond A. Yeh","orcid":"https://orcid.org/0000-0003-4375-0680"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond A. Yeh","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3420","last_page":"3424"},"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/source-separation","display_name":"Source separation","score":0.7550569772720337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300837635993958},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.700178325176239},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.599422812461853},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5730466842651367},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5420433282852173},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5302253365516663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5230435132980347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36330050230026245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3299938440322876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18887168169021606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14491260051727295},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0916050374507904}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7550569772720337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300837635993958},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.700178325176239},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.599422812461853},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5730466842651367},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5420433282852173},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5302253365516663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5230435132980347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36330050230026245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3299938440322876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18887168169021606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14491260051727295},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0916050374507904},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2031647436","https://openalex.org/W2051727797","https://openalex.org/W2127851351","https://openalex.org/W2164098335","https://openalex.org/W2221409856","https://openalex.org/W2407740810","https://openalex.org/W2734774145","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964121744","https://openalex.org/W2972767900","https://openalex.org/W3015006610","https://openalex.org/W3015199127","https://openalex.org/W3035268204","https://openalex.org/W3097201508","https://openalex.org/W6631190155","https://openalex.org/W6713927771","https://openalex.org/W6774995033","https://openalex.org/W6775488586"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W2021161555","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W4385464961","https://openalex.org/W4308092240","https://openalex.org/W4385829936","https://openalex.org/W2077498359"],"abstract_inverted_index":{"We":[0,88,102],"propose":[1,47],"an":[2],"end-to-end":[3],"trainable":[4],"approach":[5,16,91,106],"to":[6,29,52,69,99],"single-channel":[7],"speech":[8],"separation":[9,21,55],"with":[10,23,56,96],"unknown":[11],"number":[12,32,58,112],"of":[13,33,59,113,120],"speakers.":[14,60,101],"Our":[15],"extends":[17],"the":[18,31,39,43,65,71,74,82,86,93,111],"MulCat":[19],"source":[20,54],"backbone":[22],"additional":[24],"output":[25],"heads:":[26],"a":[27,48],"count-head":[28],"infer":[30],"speakers,":[34],"and":[35,115],"decoder-heads":[36],"for":[37],"reconstructing":[38],"original":[40],"signals.":[41,122],"Beyond":[42],"model,":[44],"we":[45,62],"also":[46],"metric":[49],"on":[50,67,92],"how":[51,68],"evaluate":[53,70,89],"variable":[57],"Specifically,":[61],"clear":[63],"up":[64,98],"issue":[66],"quality":[72,119],"when":[73],"ground-truth":[75],"has":[76],"more":[77],"or":[78],"less":[79],"speakers":[80,114],"than":[81],"ones":[83],"predicted":[84],"by":[85],"model.":[87],"our":[90,105],"WSJ0-mix":[94],"datasets,":[95],"mixtures":[97],"five":[100],"demonstrate":[103],"that":[104],"outperforms":[107],"state-of-the-art":[108],"in":[109,118],"counting":[110],"remains":[116],"competitive":[117],"reconstructed":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}