{"id":"https://openalex.org/W2127144047","doi":"https://doi.org/10.1109/icassp.2011.5947603","title":"Combining speaker and noise feature normalization techniques for Automatic Speech Recognition","display_name":"Combining speaker and noise feature normalization techniques for Automatic Speech Recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2127144047","doi":"https://doi.org/10.1109/icassp.2011.5947603","mag":"2127144047"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5013746163","display_name":"Luz Garc\u00eda","orcid":"https://orcid.org/0000-0001-5904-5412"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"L. Garcia","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032065113","display_name":"Carmen Ben\u0131\u0301tez","orcid":"https://orcid.org/0000-0002-5407-8335"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"C. Benitez","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"J.C. Segura","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3189,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84830939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5496","last_page":"5499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9979000091552734,"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":0.9957000017166138,"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/normalization","display_name":"Normalization (sociology)","score":0.8721638917922974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7862303853034973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7238324880599976},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7115933299064636},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6048917770385742},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5689395666122437},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.5387770533561707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5233116149902344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46551230549812317},{"id":"https://openalex.org/keywords/adaptive-histogram-equalization","display_name":"Adaptive histogram equalization","score":0.4388279318809509},{"id":"https://openalex.org/keywords/histogram-equalization","display_name":"Histogram equalization","score":0.32241326570510864},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07476642727851868}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8721638917922974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862303853034973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7238324880599976},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7115933299064636},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6048917770385742},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5689395666122437},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.5387770533561707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5233116149902344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46551230549812317},{"id":"https://openalex.org/C30387639","wikidata":"https://www.wikidata.org/wiki/Q4680744","display_name":"Adaptive histogram equalization","level":5,"score":0.4388279318809509},{"id":"https://openalex.org/C136943445","wikidata":"https://www.wikidata.org/wiki/Q1970240","display_name":"Histogram equalization","level":4,"score":0.32241326570510864},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07476642727851868},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2964579","https://openalex.org/W61316136","https://openalex.org/W257179395","https://openalex.org/W1616590059","https://openalex.org/W1992012199","https://openalex.org/W2105885996","https://openalex.org/W2112248186","https://openalex.org/W2114156775","https://openalex.org/W2143082658","https://openalex.org/W2151484683","https://openalex.org/W2164931619","https://openalex.org/W2165712617","https://openalex.org/W2171000037","https://openalex.org/W4285719527","https://openalex.org/W6600130949","https://openalex.org/W6602511383","https://openalex.org/W6609775309","https://openalex.org/W6676971917","https://openalex.org/W6677234324","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W249497648","https://openalex.org/W2162593906","https://openalex.org/W2387482914","https://openalex.org/W2385217229","https://openalex.org/W2302472796","https://openalex.org/W2376822833","https://openalex.org/W2393164332","https://openalex.org/W4319781082","https://openalex.org/W2015245117","https://openalex.org/W2604503469"],"abstract_inverted_index":{"This":[0],"work":[1],"deals":[2],"with":[3],"strategies":[4],"to":[5,42,80],"jointly":[6],"reduce":[7],"the":[8,23,35,38,43,54,82,85],"speaker":[9],"and":[10,66,70,78],"environment":[11],"mismatches":[12],"in":[13,22,58,68],"Automatic":[14],"Speech":[15],"Recognition.":[16],"The":[17],"consequences":[18],"of":[19,25,37,56,84],"environmental":[20],"mismatch":[21],"performance":[24],"conventional":[26],"Vocal":[27],"Tract":[28],"Length":[29],"Normalization":[30],"algorithm":[31],"are":[32,76],"analyzed,":[33],"observing":[34],"sensitivity":[36],"warping":[39],"factor":[40],"distributions":[41],"SNR":[44],"fall.":[45],"A":[46],"new":[47],"combined":[48],"speaker-noise":[49],"normalization":[50],"strategy":[51],"which":[52],"reduces":[53],"effect":[55],"noise":[57],"VTLN":[59],"by":[60],"applying":[61],"Histogram":[62],"Equalization":[63],"is":[64],"proposed":[65],"experimented":[67],"AURORA2":[69],"AU":[71],"RORA4":[72],"databases.":[73],"Solid":[74],"results":[75],"obtained":[77],"discussed":[79],"analyze":[81],"effectiveness":[83],"described":[86],"technique.":[87]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}