{"id":"https://openalex.org/W2110878662","doi":"https://doi.org/10.1109/icassp.2010.5495567","title":"Non-negative matrix factorization as noise-robust feature extractor for speech recognition","display_name":"Non-negative matrix factorization as noise-robust feature extractor for speech recognition","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2110878662","doi":"https://doi.org/10.1109/icassp.2010.5495567","mag":"2110878662"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495567","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=1082475","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 Arcisstrasse 21, 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 Arcisstrasse 21, 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":"middle","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 Arcisstrasse 21, 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 Arcisstrasse 21, 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":"middle","author":{"id":"https://openalex.org/A5068023895","display_name":"Martin W\u00f6llmer","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":"Martin Wollmer","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen Arcisstrasse 21, 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 Arcisstrasse 21, 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":"middle","author":{"id":"https://openalex.org/A5100714901","display_name":"Yang Sun","orcid":"https://orcid.org/0000-0002-5483-0953"},"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":"Yang Sun","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen Arcisstrasse 21, 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 Arcisstrasse 21, 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/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"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":"Gerhard Rigoll","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen Arcisstrasse 21, 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 Arcisstrasse 21, 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":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4562","last_page":"4565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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":0.8912724256515503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532045841217041},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6841204166412354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6485141515731812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6038111448287964},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5810637474060059},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5670042634010315},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48892274498939514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48654261231422424},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4604203999042511},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4377850294113159},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1390799880027771}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8912724256515503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532045841217041},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6841204166412354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6485141515731812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6038111448287964},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5810637474060059},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5670042634010315},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48892274498939514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48654261231422424},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4604203999042511},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4377850294113159},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1390799880027771},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495567","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:10.1.1.364.3855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.3855","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/10/10sch3.pdf","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1082475","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1082475","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:76319","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-763192","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/1082475","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1082475","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W24721013","https://openalex.org/W104438260","https://openalex.org/W185399533","https://openalex.org/W195578718","https://openalex.org/W1515206890","https://openalex.org/W1566256432","https://openalex.org/W1598897359","https://openalex.org/W2064675550","https://openalex.org/W2095619312","https://openalex.org/W2114217273","https://openalex.org/W2117172387","https://openalex.org/W2120987913","https://openalex.org/W2135029798","https://openalex.org/W2150415460","https://openalex.org/W2158291955","https://openalex.org/W2745539906","https://openalex.org/W2883491318","https://openalex.org/W3143596294","https://openalex.org/W4285719527","https://openalex.org/W6607486085","https://openalex.org/W6630569557","https://openalex.org/W6633947590","https://openalex.org/W6636006897","https://openalex.org/W6674174934","https://openalex.org/W6680012447","https://openalex.org/W6683202405","https://openalex.org/W6753440864"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"We":[0,52,86],"introduce":[1],"a":[2,48,54,66,77,107],"novel":[3],"approach":[4],"for":[5,24],"noise-robust":[6],"feature":[7],"extraction":[8],"in":[9,65,106],"speech":[10,25],"recognition,":[11],"based":[12],"on":[13],"non-negative":[14],"matrix":[15],"factorization":[16],"(NMF).":[17],"While":[18],"NMF":[19,37,46,91],"has":[20],"previously":[21],"been":[22],"used":[23],"denoising":[26],"and":[27],"speaker":[28],"separation,":[29],"we":[30,42],"directly":[31],"extract":[32],"time-varying":[33],"features":[34,64,92],"from":[35],"the":[36,71],"output.":[38],"To":[39],"this":[40],"end":[41],"extend":[43],"basic":[44],"unsupervised":[45],"to":[47,93,103],"hybrid":[49],"supervised/unsupervised":[50],"algorithm.":[51],"present":[53],"Dynamic":[55],"Bayesian":[56],"Network":[57],"(DBN)":[58],"architecture":[59],"that":[60,88],"can":[61,97],"exploit":[62],"these":[63],"Tandem":[67],"manner":[68],"together":[69],"with":[70],"maximum":[72],"likelihood":[73],"phoneme":[74],"estimate":[75],"of":[76,90],"bidirectional":[78],"long":[79],"short-term":[80],"memory":[81],"(BLSTM)":[82],"recurrent":[83],"neural":[84],"network.":[85],"show":[87],"addition":[89],"spelling":[94],"recognition":[95],"systems":[96],"increase":[98],"word":[99],"accuracy":[100],"by":[101],"up":[102],"7%":[104],"absolute":[105],"noisy":[108],"car":[109],"environment.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
