{"id":"https://openalex.org/W2403025337","doi":"https://doi.org/10.21437/interspeech.2011-203","title":"Semi-supervised single-channel speech-music separation for automatic speech recognition","display_name":"Semi-supervised single-channel speech-music separation for automatic speech recognition","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2403025337","doi":"https://doi.org/10.21437/interspeech.2011-203","mag":"2403025337"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","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/A5006515267","display_name":"Cemil Demir","orcid":"https://orcid.org/0000-0002-6365-0196"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cemil Demir","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064633247","display_name":"Ali Taylan Cemgil","orcid":"https://orcid.org/0000-0003-4463-8455"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. Taylan Cemgil","raw_affiliation_strings":["Bogazi\u00e7i University"],"affiliations":[{"raw_affiliation_string":"Bogazi\u00e7i University","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Murat Sara\u00e7lar","raw_affiliation_strings":["Bogazi\u00e7i University"],"affiliations":[{"raw_affiliation_string":"Bogazi\u00e7i University","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006515267"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2249,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81256238,"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":"681","last_page":"684"},"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":0.9995999932289124,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8462885022163391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7817702293395996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569998502731323},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5564386248588562},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5097605586051941},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4936002492904663},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4698067307472229},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.46924710273742676},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.44992291927337646},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4293396472930908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4129626750946045},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.35232365131378174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06506535410881042}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8462885022163391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7817702293395996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569998502731323},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5564386248588562},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5097605586051941},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4936002492904663},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4698067307472229},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.46924710273742676},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.44992291927337646},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4293396472930908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4129626750946045},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.35232365131378174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06506535410881042},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W76921649","https://openalex.org/W146976060","https://openalex.org/W185399533","https://openalex.org/W196049401","https://openalex.org/W1963835294","https://openalex.org/W2031696998","https://openalex.org/W2115283881","https://openalex.org/W2117150818","https://openalex.org/W2150415460","https://openalex.org/W2164162335"],"related_works":["https://openalex.org/W2547262076","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W1565566036","https://openalex.org/W2921513691","https://openalex.org/W2534043196","https://openalex.org/W2098101267","https://openalex.org/W2615370628","https://openalex.org/W1911859126","https://openalex.org/W642007152"],"abstract_inverted_index":{"In":[0,38],"this":[1,39],"study,":[2],"we":[3,41,64],"propose":[4],"a":[5,19,66],"semi-supervised":[6],"speech-music":[7,16,36],"separation":[8,112],"method":[9,117],"which":[10],"uses":[11],"the":[12,34,43,47,54,57,61,71,89,93,99,105,109,115],"speech,":[13],"music":[14,28,45,58,72],"and":[15,27,102],"segments":[17],"in":[18,33,60,120],"given":[20],"segmented":[21],"audio":[22],"signal":[23,49,76],"to":[24,69],"separate":[25],"speech":[26,75,100,122],"signals":[29],"from":[30],"each":[31],"other":[32],"mixed":[35,48,106],"segments.":[37],"strategy,":[40],"assume,":[42],"background":[44],"of":[46,53,56,88,92,108,114],"is":[50,77,96,118],"partially":[51],"composed":[52],"repetition":[55],"segment":[59,101,107],"audio.":[62,110],"Therefore,":[63],"used":[65],"mixture":[67],"model":[68,87,95],"represent":[70],"signal.":[73],"The":[74,85,111],"modeled":[78],"using":[79,98,104],"Non-negative":[80],"Matrix":[81],"Factorization":[82],"(NMF)":[83],"model.":[84],"prior":[86],"template":[90],"matrix":[91],"NMF":[94],"estimated":[97],"updated":[103],"performance":[113],"proposed":[116],"evaluated":[119],"automatic":[121],"recognition":[123],"task.":[124]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
