{"id":"https://openalex.org/W2036245667","doi":"https://doi.org/10.1109/icassp.2014.6854302","title":"Discriminative non-negative matrix factorization for single-channel speech separation","display_name":"Discriminative non-negative matrix factorization for single-channel speech separation","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2036245667","doi":"https://doi.org/10.1109/icassp.2014.6854302","mag":"2036245667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5100338332","display_name":"Zi Wang","orcid":"https://orcid.org/0000-0002-5081-661X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544732","display_name":"Fei Sha","orcid":"https://orcid.org/0000-0002-9382-0010"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Sha","raw_affiliation_strings":["Department of Computer Science, University of Southern California, Los Angeles, CA","Department of Computer Science University of Southern California Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science University of Southern California Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3749","last_page":"3753"},"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":0.9987000226974487,"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":0.9976000189781189,"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":0.8878052234649658},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8724716901779175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387658953666687},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6616993546485901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400920152664185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6217499375343323},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6151167750358582},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.5662431716918945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537834882736206},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5279882550239563},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41550183296203613},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4132320284843445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22797852754592896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19322291016578674},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13590657711029053},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06165853142738342}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8878052234649658},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8724716901779175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387658953666687},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6616993546485901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400920152664185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6217499375343323},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6151167750358582},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5662431716918945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537834882736206},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5279882550239563},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41550183296203613},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4132320284843445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22797852754592896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19322291016578674},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13590657711029053},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06165853142738342},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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.2014.6854302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306230","display_name":"American Heart Association","ror":"https://ror.org/013kjyp64"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W141691577","https://openalex.org/W185399533","https://openalex.org/W1902027874","https://openalex.org/W1964538581","https://openalex.org/W1983133367","https://openalex.org/W2015143272","https://openalex.org/W2104298926","https://openalex.org/W2116216716","https://openalex.org/W2118522520","https://openalex.org/W2130789253","https://openalex.org/W2135029798","https://openalex.org/W2147437692","https://openalex.org/W2150415460","https://openalex.org/W2315268655","https://openalex.org/W2402209653","https://openalex.org/W2405716592","https://openalex.org/W3143596294","https://openalex.org/W6605853566","https://openalex.org/W6607486085","https://openalex.org/W6677633546","https://openalex.org/W6680012447","https://openalex.org/W6713734294"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2900450731"],"abstract_inverted_index":{"Non-negative":[0],"matrix":[1],"factorization":[2],"(NMF)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,19,74],"promising":[8],"approach":[9,46],"for":[10,81],"single-channel":[11],"speech":[12],"separation.":[13],"In":[14,27],"this":[15],"paper,":[16],"we":[17],"propose":[18],"new":[20],"method":[21],"of":[22,25],"discriminative":[23,68],"learning":[24],"NMF.":[26],"contrast":[28],"to":[29,52],"conventional":[30],"approaches":[31],"where":[32],"the":[33],"basis":[34,49],"vectors":[35,50],"are":[36],"learned":[37],"independently":[38],"on":[39],"clean":[40,55],"signals":[41,56,59],"from":[42],"each":[43],"speaker,":[44],"our":[45,65],"optimizes":[47],"all":[48],"jointly":[51],"reconstruct":[53],"both":[54],"and":[57],"mixed":[58],"well.":[60],"Our":[61],"empirical":[62],"studies":[63],"validated":[64],"approach.":[66],"Specifically,":[67],"NMF":[69],"outperforms":[70],"standard":[71],"methods":[72],"by":[73],"large":[75],"margin":[76],"in":[77],"improving":[78],"signal-to-noise":[79],"ratio":[80],"reconstructing":[82],"signals.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}