{"id":"https://openalex.org/W1991728432","doi":"https://doi.org/10.1109/icassp.2010.5495061","title":"Discrimination of speech and non-linguistic vocalizations by Non-Negative Matrix Factorization","display_name":"Discrimination of speech and non-linguistic vocalizations by Non-Negative Matrix Factorization","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W1991728432","doi":"https://doi.org/10.1109/icassp.2010.5495061","mag":"1991728432"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1082473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, Munchen, Germany","Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Arcisstrasse 21, D-80333, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Arcisstrasse 21, D-80333, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","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, Munchen, Germany","Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Arcisstrasse 21, D-80333, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Arcisstrasse 21, D-80333, 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":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5054","last_page":"5057"},"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":0.9994999766349792,"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":0.996999979019165,"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":0.8662356734275818},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.764915943145752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483273148536682},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.5827208757400513},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5741047263145447},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.536258339881897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341431498527527},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.48574692010879517},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4726383090019226},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4342588782310486},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4292309880256653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.401760458946228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36428362131118774},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09334224462509155}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8662356734275818},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.764915943145752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483273148536682},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.5827208757400513},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5741047263145447},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.536258339881897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341431498527527},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.48574692010879517},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4726383090019226},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4342588782310486},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4292309880256653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.401760458946228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36428362131118774},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09334224462509155},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4071","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4071","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/10/10sch5.pdf","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1082473","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1082473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76289","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-762893","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":{"id":"pmh:oai:mediatum.ub.tum.de:node/1082473","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1082473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W83793253","https://openalex.org/W104438260","https://openalex.org/W152150158","https://openalex.org/W185399533","https://openalex.org/W198720948","https://openalex.org/W309418507","https://openalex.org/W1489056342","https://openalex.org/W1503417225","https://openalex.org/W1515206890","https://openalex.org/W1598897359","https://openalex.org/W1838628832","https://openalex.org/W2032382719","https://openalex.org/W2095619312","https://openalex.org/W2114217273","https://openalex.org/W2135029798","https://openalex.org/W2140035970","https://openalex.org/W2150415460","https://openalex.org/W2158291955","https://openalex.org/W3143596294","https://openalex.org/W4213231615","https://openalex.org/W6603409251","https://openalex.org/W6606192499","https://openalex.org/W6610803811","https://openalex.org/W6630569557","https://openalex.org/W6636006897","https://openalex.org/W6674174934","https://openalex.org/W6677054355","https://openalex.org/W6680012447","https://openalex.org/W6683202405"],"related_works":["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/W34555840","https://openalex.org/W2146544734"],"abstract_inverted_index":{"We":[0],"introduce":[1],"features":[2,103],"based":[3,78],"on":[4,79],"Non-Negative":[5],"Matrix":[6],"Factorization":[7],"(NMF)":[8],"for":[9,54],"discrimination":[10],"of":[11,28,65,83,101,111,123,135],"speech":[12,56,95,112],"and":[13,42,113,120],"non-linguistic":[14,114],"vocalizations":[15,115],"such":[16,39],"as":[17,40,50],"laughter":[18,124],"or":[19],"breathing,":[20],"which":[21],"is":[22,130],"a":[23,51,74,80,93,133],"crucial":[24],"task":[25],"in":[26,36],"recognition":[27],"spontaneous":[29,94],"speech.":[30],"NMF":[31,67,102],"has":[32],"been":[33],"successfully":[34],"used":[35],"speech-related":[37],"tasks":[38],"de-noising":[41],"speaker":[43],"separation.":[44],"While":[45],"existing":[46],"approaches":[47],"use":[48],"it":[49],"preprocessing":[52],"step":[53],"conventional":[55],"recognizers,":[57],"we":[58,72,97],"aim":[59],"at":[60,132],"directly":[61],"classifying":[62],"the":[63,66],"output":[64],"algorithm.":[68],"To":[69],"this":[70],"end,":[71],"propose":[73],"feature":[75],"extraction":[76],"procedure":[77],"supervised":[81],"variant":[82],"NMF,":[84],"considering":[85],"two":[86],"different":[87],"algorithms.":[88],"Applying":[89],"our":[90],"approach":[91],"to":[92,104],"corpus,":[96],"show":[98],"that":[99],"addition":[100],"an":[105],"MFCC-based":[106],"classifier":[107],"increases":[108],"mean":[109],"recall":[110,122],"by":[116,125],"over":[117],"2.5%":[118],"absolute,":[119],"particularly":[121],"6.6%":[126],"absolute.":[127],"The":[128],"improvement":[129],"significant":[131],"level":[134],"0.4":[136],"%.":[137]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}