{"id":"https://openalex.org/W2398777594","doi":"https://doi.org/10.1109/icassp.2016.7471651","title":"A source/filter model with adaptive constraints for NMF-based speech separation","display_name":"A source/filter model with adaptive constraints for NMF-based speech separation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398777594","doi":"https://doi.org/10.1109/icassp.2016.7471651","mag":"2398777594"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5108270170","display_name":"Bouvier Damien","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Damien Bouvier","raw_affiliation_strings":["IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062200666","display_name":"Marco Liuni","orcid":"https://orcid.org/0000-0001-6831-8259"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marco Liuni","raw_affiliation_strings":["IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065828059","display_name":"Axel R\u00f6ebel","orcid":"https://orcid.org/0000-0001-6136-4391"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Roebel","raw_affiliation_strings":["IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM - UMR STMS IRCAM-CNRS-UPMC Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108270170"],"corresponding_institution_ids":["https://openalex.org/I39804081","https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"],"apc_list":null,"apc_paid":null,"fwci":0.71433316,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71978177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"135"},"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":0.9991999864578247,"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":0.9988999962806702,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8299996852874756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737055778503418},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6726261377334595},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6552101969718933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6419072151184082},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5503923892974854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4662887752056122},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.4610430896282196},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.422024667263031},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4129159450531006},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.41108131408691406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3672862648963928},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3462219834327698},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.20713451504707336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16507628560066223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13396593928337097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06843343377113342}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8299996852874756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737055778503418},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6726261377334595},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6552101969718933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6419072151184082},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5503923892974854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4662887752056122},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.4610430896282196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.422024667263031},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4129159450531006},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41108131408691406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3672862648963928},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3462219834327698},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.20713451504707336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16507628560066223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13396593928337097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06843343377113342},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W46110029","https://openalex.org/W1506438021","https://openalex.org/W1552314771","https://openalex.org/W1555814299","https://openalex.org/W1571887930","https://openalex.org/W1601892841","https://openalex.org/W1902027874","https://openalex.org/W1974186229","https://openalex.org/W2001987918","https://openalex.org/W2004125252","https://openalex.org/W2043095867","https://openalex.org/W2045956438","https://openalex.org/W2062507334","https://openalex.org/W2068144845","https://openalex.org/W2098446659","https://openalex.org/W2114352222","https://openalex.org/W2114508388","https://openalex.org/W2127851351","https://openalex.org/W2134807719","https://openalex.org/W2136171036","https://openalex.org/W2150415460"],"related_works":["https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2146544734","https://openalex.org/W1979654135","https://openalex.org/W2156699640","https://openalex.org/W2156181515","https://openalex.org/W2158112352","https://openalex.org/W2098101267","https://openalex.org/W2081322759","https://openalex.org/W1984255382"],"abstract_inverted_index":{"This":[0,160],"paper":[1],"introduces":[2],"a":[3,29,37,76,90,121],"constrained":[4,134],"source/filter":[5,38,84,106,135,174],"model":[6,39,107,175],"for":[7,92,117,140,176],"semi-supervised":[8],"speech":[9,32,77,87,141,178,185],"separation":[10,100,142],"based":[11,81],"on":[12,82,145],"non-negative":[13],"matrix":[14],"factorization":[15],"(NMF).":[16],"The":[17],"objective":[18],"is":[19,47,108,115],"to":[20,56,61,69,183],"inform":[21],"NMF":[22,64],"with":[23,151],"prior":[24],"knowledge":[25],"about":[26],"speech,":[27],"providing":[28],"physically":[30],"meaningful":[31],"separation.":[33,186],"To":[34],"do":[35],"so,":[36],"(indicated":[40],"as":[41],"Instantaneous":[42],"Mixture":[43],"Model":[44],"or":[45],"IMM)":[46],"integrated":[48],"in":[49,59,132],"the":[50,57,63,83,93,104,125,133,146,157,164,170,173],"NMF.":[51],"Furthermore,":[52],"constraints":[53,168],"are":[54,101,129],"added":[55],"IMM-NMF,":[58],"order":[60],"control":[62],"behaviour":[65],"during":[66,99,110,123],"separation,":[67,124,179],"and":[68,89,180],"enforce":[70],"its":[71],"physical":[72],"meaning.":[73],"In":[74],"particular,":[75],"specific":[78],"constraint":[79],"-":[80,88],"coherence":[85],"of":[86,96,120,166,172],"method":[91],"automatic":[94],"adaptation":[95],"constraints'":[97],"weights":[98],"presented.":[102],"Also,":[103],"proposed":[105],"semi-supervised:":[109],"training,":[111],"one":[112],"filter":[113,127],"basis":[114],"estimated":[116,126],"each":[118],"phoneme":[119],"speaker;":[122],"bases":[128],"then":[130],"used":[131],"model.":[136],"An":[137],"experimental":[138],"evaluation":[139,161],"was":[143],"conducted":[144],"TIMIT":[147],"speakers":[148],"database":[149],"mixed":[150],"various":[152],"environmental":[153],"background":[154],"noises":[155],"from":[156],"QUT-NOISE":[158],"database.":[159],"showed":[162],"that":[163],"use":[165],"adaptive":[167],"increases":[169],"performance":[171],"speaker-dependent":[177],"compares":[181],"favorably":[182],"fully-supervised":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}