{"id":"https://openalex.org/W2109258319","doi":"https://doi.org/10.1109/icassp.2011.5946384","title":"Joint unsupervised learning of hidden Markov source models and source location models for multichannel source separation","display_name":"Joint unsupervised learning of hidden Markov source models and source location models for multichannel source separation","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2109258319","doi":"https://doi.org/10.1109/icassp.2011.5946384","mag":"2109258319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/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, Soraku-gun, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"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":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, 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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"240"},"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":0.9975000023841858,"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":0.9972000122070312,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8483282327651978},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7561284899711609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506906986236572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5578612685203552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5466578006744385},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5389081239700317},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5227732062339783},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4939647316932678},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4669764041900635},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42941418290138245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.091106116771698}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8483282327651978},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7561284899711609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506906986236572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5578612685203552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5466578006744385},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5389081239700317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5227732062339783},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4939647316932678},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4669764041900635},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42941418290138245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.091106116771698},{"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W21035339","https://openalex.org/W44831635","https://openalex.org/W1987906574","https://openalex.org/W2029564985","https://openalex.org/W2144271355","https://openalex.org/W2166458192","https://openalex.org/W6601817925"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W2889447638","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2107688514","https://openalex.org/W2137288760","https://openalex.org/W3121710301"],"abstract_inverted_index":{"This":[0],"paper":[1,99],"discusses":[2],"a":[3,65,101],"multichannel":[4],"source":[5,14,26,61],"separation":[6,85,132],"approach":[7],"that":[8,40,125],"exploits":[9],"the":[10,41,53,75,79,84,89,105,108,115,118,126],"statistical":[11],"characteristics":[12],"of":[13,25,43,55,91,107,114,133],"location":[15,62],"cues":[16,63],"characterized":[17,29],"by":[18,30],"steering":[19],"vector":[20],"models":[21,33],"(SM)":[22],"and":[23,78],"those":[24,113],"log":[27],"spectra":[28],"hidden":[31],"Markov":[32],"(spectral":[34],"HMM).":[35],"Recently,":[36],"it":[37],"was":[38],"shown":[39],"use":[42],"speaker":[44],"independent":[45],"spectral":[46,76,109],"HMMs":[47,77,110],"trained":[48],"in":[49,64],"advance":[50],"substantially":[51,82],"improves":[52],"quality":[54],"speech":[56],"signals":[57],"separated":[58],"based":[59],"on":[60],"computationally":[66],"efficient":[67],"manner.":[68],"However,":[69],"with":[70,112],"this":[71,92,96,98],"approach,":[72],"mismatches":[73],"between":[74],"observation":[80],"may":[81],"degrade":[83],"quality,":[86],"which":[87],"limits":[88],"applicability":[90],"approach.":[93],"To":[94],"overcome":[95],"problem,":[97],"proposes":[100],"method":[102,128],"for":[103,131],"learning":[104],"parameters":[106],"jointly":[111],"SMs":[116],"from":[117],"observed":[119],"sound":[120,135],"mixtures.":[121,136],"Experimental":[122],"results":[123],"show":[124],"proposed":[127],"works":[129],"effectively":[130],"convolutive":[134]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}