{"id":"https://openalex.org/W2147437692","doi":"https://doi.org/10.1109/icassp.2012.6287817","title":"Supervised and semi-supervised suppression of background music in monaural speech recordings","display_name":"Supervised and semi-supervised suppression of background music in monaural speech recordings","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2147437692","doi":"https://doi.org/10.1109/icassp.2012.6287817","mag":"2147437692"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112058690","display_name":"Jordi Feli\u00fa","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jordi Feliu","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"64"},"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.8515320420265198},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7622500658035278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134885191917419},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6954531669616699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6657828688621521},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5718716979026794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5486881136894226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5121710300445557},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.48914864659309387},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43285804986953735},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.42406490445137024},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4115006625652313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15960153937339783},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.15903109312057495}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8515320420265198},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7622500658035278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134885191917419},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6954531669616699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6657828688621521},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5718716979026794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5486881136894226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5121710300445557},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.48914864659309387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43285804986953735},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.42406490445137024},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4115006625652313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15960153937339783},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.15903109312057495},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6287817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.3626","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.3626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/12/12wen2.pdf","raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72651","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-726516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W1504438288","https://openalex.org/W1984059267","https://openalex.org/W2115109087","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2141520175","https://openalex.org/W2150415460","https://openalex.org/W2155531311","https://openalex.org/W2168826081","https://openalex.org/W6606052675"],"related_works":["https://openalex.org/W2929481141","https://openalex.org/W2955471771","https://openalex.org/W3013896298","https://openalex.org/W2897917529","https://openalex.org/W2987870598","https://openalex.org/W3097681199","https://openalex.org/W2892198678","https://openalex.org/W2902298602","https://openalex.org/W2031647436","https://openalex.org/W2013531086"],"abstract_inverted_index":{"In":[0,26,58],"this":[1],"paper,":[2],"we":[3,70],"propose":[4],"a":[5,59],"semi-supervised":[6,73,89],"algorithm":[7],"based":[8],"on":[9,102],"sparse":[10],"non-negative":[11],"matrix":[12],"factorization":[13],"(NMF)":[14],"to":[15,44,75,106],"improve":[16,110],"separation":[17,111],"of":[18],"speech":[19,30],"from":[20,35,66],"background":[21,81],"music":[22,39,82,104],"in":[23],"monaural":[24],"signals.":[25],"our":[27],"approach,":[28],"fixed":[29],"basis":[31],"vectors":[32],"are":[33,41],"obtained":[34],"training":[36],"data":[37],"whereas":[38],"bases":[40],"estimated":[42],"on-the-fly":[43],"cope":[45],"with":[46,63,78],"spectral":[47],"variability":[48],"while":[49],"preserving":[50],"small":[51],"NMF":[52,77,93],"dimensionality":[53],"for":[54],"decreased":[55],"computation":[56],"effort.":[57],"large-scale":[60],"experimental":[61],"evaluation":[62],"168":[64],"speakers":[65],"the":[67,72,88,103],"TIMIT":[68],"database,":[69],"compare":[71],"method":[74,90],"supervised":[76,92],"an":[79],"explicit":[80],"model.":[83],"Our":[84],"results":[85],"reveal":[86],"that":[87,99],"outperforms":[91],"at":[94],"low":[95],"speech-to-music":[96],"ratios,":[97],"and":[98],"sparsity":[100],"constraints":[101],"spectra":[105],"enforce":[107],"harmonicity":[108],"can":[109],"performance.":[112]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}