{"id":"https://openalex.org/W2408564927","doi":"https://doi.org/10.1109/icassp.2016.7472776","title":"CNMF-based acoustic features for noise-robust ASR","display_name":"CNMF-based acoustic features for noise-robust ASR","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408564927","doi":"https://doi.org/10.1109/icassp.2016.7472776","mag":"2408564927"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5082491203","display_name":"Colin Vaz","orcid":"https://orcid.org/0000-0002-5709-7953"},"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":true,"raw_author_name":"Colin Vaz","raw_affiliation_strings":["Signal Analysis and Interpretation Lab, University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":["IBM, T. J. Watson Research Laboratory, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM, T. J. Watson Research Laboratory, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM, T. J. Watson Research Laboratory, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM, T. J. Watson Research Laboratory, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"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":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Lab, University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082491203"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02690528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7288357615470886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223495244979858},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6573350429534912},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6217668056488037},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5845806002616882},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.584068238735199},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5597189664840698},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5183088183403015},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5002956390380859},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4987146854400635},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4751284420490265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4513789415359497},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42700862884521484},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.373244047164917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36686062812805176},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09588262438774109},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07779192924499512}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7288357615470886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223495244979858},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6573350429534912},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6217668056488037},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5845806002616882},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.584068238735199},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5597189664840698},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5183088183403015},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5002956390380859},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4987146854400635},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4751284420490265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4513789415359497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42700862884521484},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.373244047164917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36686062812805176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09588262438774109},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07779192924499512},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","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/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.2016.7472776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W71792008","https://openalex.org/W1279245896","https://openalex.org/W1517348348","https://openalex.org/W1950777589","https://openalex.org/W1976637928","https://openalex.org/W2035576074","https://openalex.org/W2057826000","https://openalex.org/W2059745395","https://openalex.org/W2062164080","https://openalex.org/W2088817208","https://openalex.org/W2102953093","https://openalex.org/W2104104263","https://openalex.org/W2114719288","https://openalex.org/W2118497033","https://openalex.org/W2118718620","https://openalex.org/W2120847449","https://openalex.org/W2124149378","https://openalex.org/W2126597753","https://openalex.org/W2127544007","https://openalex.org/W2128653836","https://openalex.org/W2135029798","https://openalex.org/W2150769028","https://openalex.org/W2155117693","https://openalex.org/W3143596294","https://openalex.org/W6630687167","https://openalex.org/W6664675605","https://openalex.org/W6677759377","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W2919389044","https://openalex.org/W1997528538","https://openalex.org/W2777466939","https://openalex.org/W2889693761","https://openalex.org/W2890579888","https://openalex.org/W1966856063","https://openalex.org/W2900450731","https://openalex.org/W2593427229","https://openalex.org/W2401089611","https://openalex.org/W2022538999"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"algorithm":[3],"using":[4,53,110],"convolutive":[5],"non-negative":[6],"matrix":[7],"factorization":[8],"(CNMF)":[9],"to":[10,26,33,69,109,140],"create":[11,70],"noise-robust":[12,21,77],"features":[13,136],"for":[14],"automatic":[15],"speech":[16,31,71],"recognition":[17],"(ASR).":[18],"Typically":[19],"in":[20,98],"ASR,":[22],"CNMF":[23,58],"is":[24],"used":[25],"remove":[27],"noise":[28,73],"from":[29,57,80],"noisy":[30,81],"prior":[32],"feature":[34],"extraction.":[35],"However,":[36],"we":[37,51,66,92,115,126],"find":[38],"that":[39,75,134],"denoising":[40],"introduces":[41],"distortion":[42],"and":[43,72],"artifacts,":[44],"which":[45],"can":[46],"degrade":[47],"ASR":[48],"performance.":[49],"Instead,":[50],"propose":[52],"the":[54,84,99,104],"time-activation":[55,78,85],"matrices":[56,79,86],"as":[59],"acoustic":[60],"model":[61],"features.":[62,142],"In":[63],"this":[64],"paper,":[65],"describe":[67],"how":[68],"dictionaries":[74],"generate":[76],"speech.":[82],"Using":[83],"created":[87],"by":[88],"our":[89,130,135],"proposed":[90,131],"algorithm,":[91],"achieve":[93],"a":[94,117],"11.8%":[95],"relative":[96,119],"improvement":[97,120],"word":[100],"error":[101],"rate":[102],"on":[103],"Aurora":[105],"4":[106],"corpus":[107],"compared":[108],"log-mel":[111,122,141],"filterbank":[112,123],"energies.":[113],"Furthermore,":[114],"attain":[116],"13.8%":[118],"over":[121],"energies":[124],"when":[125],"combine":[127],"them":[128],"with":[129],"features,":[132],"indicating":[133],"contain":[137],"complementary":[138],"information":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}