{"id":"https://openalex.org/W2684375874","doi":"https://doi.org/10.1109/icassp.2017.7952216","title":"Bayesian multichannel nonnegative matrix factorization for audio source separation and localization","display_name":"Bayesian multichannel nonnegative matrix factorization for audio source separation and localization","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2684375874","doi":"https://doi.org/10.1109/icassp.2017.7952216","mag":"2684375874"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5073445085","display_name":"Kousuke Itakura","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kousuke Itakura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043140898","display_name":"Eita Nakamura","orcid":"https://orcid.org/0000-0003-4097-6027"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"551","last_page":"555"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9998999834060669,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.686260998249054},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6191627979278564},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5812849998474121},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.5608030557632446},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.552939772605896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5491334795951843},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5485303401947021},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5081415176391602},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4584611654281616},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.44590580463409424},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.43580561876296997},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42938217520713806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4093259274959564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3677149713039398},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3647541403770447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34179747104644775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33326053619384766},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.24161607027053833},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08835381269454956},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0693407654762268}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.686260998249054},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6191627979278564},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5812849998474121},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.5608030557632446},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.552939772605896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5491334795951843},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5485303401947021},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5081415176391602},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4584611654281616},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.44590580463409424},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.43580561876296997},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42938217520713806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4093259274959564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3677149713039398},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3647541403770447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34179747104644775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33326053619384766},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.24161607027053833},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08835381269454956},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0693407654762268},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":33,"referenced_works":["https://openalex.org/W87112183","https://openalex.org/W1521340514","https://openalex.org/W1548669759","https://openalex.org/W1755563775","https://openalex.org/W1974647903","https://openalex.org/W2012910847","https://openalex.org/W2031583051","https://openalex.org/W2054221677","https://openalex.org/W2072548008","https://openalex.org/W2074134755","https://openalex.org/W2096855653","https://openalex.org/W2104298926","https://openalex.org/W2108207895","https://openalex.org/W2113526703","https://openalex.org/W2113990625","https://openalex.org/W2123649031","https://openalex.org/W2127851351","https://openalex.org/W2129171989","https://openalex.org/W2163738067","https://openalex.org/W2168273590","https://openalex.org/W2183821610","https://openalex.org/W2217477878","https://openalex.org/W2401820494","https://openalex.org/W2408744528","https://openalex.org/W2470294693","https://openalex.org/W2480977715","https://openalex.org/W2562809169","https://openalex.org/W2963691001","https://openalex.org/W4231517135","https://openalex.org/W6631254342","https://openalex.org/W6663819358","https://openalex.org/W6677017536","https://openalex.org/W6684562281"],"related_works":["https://openalex.org/W2351387116","https://openalex.org/W2361100278","https://openalex.org/W1658347130","https://openalex.org/W2547262076","https://openalex.org/W2398836525","https://openalex.org/W2563421448","https://openalex.org/W1565566036","https://openalex.org/W1509813908","https://openalex.org/W2774154397","https://openalex.org/W2921513691"],"abstract_inverted_index":{"This":[0,134],"paper":[1],"presents":[2],"a":[3,22,51,57,88,102,113,124,140],"Bayesian":[4,104],"extension":[5],"of":[6,17,36,56,72,106,148,170,190],"multichannel":[7],"nonnegative":[8],"matrix":[9,122,128,144],"factorization":[10],"(MNMF)":[11],"that":[12,86,154],"decomposes":[13],"the":[14,32,40,44,92,146,158,162,176,191],"complex":[15],"spectrograms":[16],"mixture":[18],"signals":[19],"recorded":[20],"by":[21,111,117],"microphone":[23,58,93],"array":[24,59,94],"into":[25],"basis":[26],"spectra,":[27],"their":[28],"temporal":[29],"activations,":[30],"and":[31,109,145,161],"spatial":[33,120,126,142],"correlation":[34,70,121,127,143],"matrices":[35],"sources":[37],"(directions)":[38],"in":[39,50,78,87,168,180],"time-frequency-channel":[41],"domain.":[42],"Although":[43],"original":[45,159],"MNMF":[46,160],"can":[47,75],"be":[48,76],"used":[49,179],"blind":[52],"setting,":[53],"prior":[54,114,166],"knowledge":[55,167],"is":[60,95],"useful":[61],"for":[62],"improving":[63],"source":[64,107],"separation.":[65],"The":[66],"impulse":[67],"response":[68],"(spatial":[69],"matrix)":[71],"each":[73,132,149],"direction":[74,147],"measured":[77],"an":[79,118,181],"anechoic":[80,119,192],"room,":[81],"however,":[82],"it":[83],"differs":[84],"from":[85,188],"real":[89,125,141],"environment":[90,183],"where":[91],"used.":[96],"To":[97],"solve":[98],"this,":[99],"we":[100],"propose":[101],"unified":[103],"model":[105],"separation":[108],"localization":[110],"introducing":[112],"distribution":[115],"determined":[116],"on":[123],"with":[129,165,184],"respect":[130],"to":[131,137],"direction.":[133],"enables":[135],"us":[136],"adaptively":[138],"estimate":[139],"source.":[150],"Experimental":[151],"results":[152],"showed":[153],"our":[155],"method":[156,177],"outperformed":[157],"state-of-the-art":[163],"methods":[164],"terms":[169],"signal-to-distortion":[171],"ratio":[172],"(SDR)":[173],"even":[174],"when":[175],"was":[178],"unknown":[182],"acoustic":[185],"characteristics":[186],"different":[187],"those":[189],"room.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}