{"id":"https://openalex.org/W2117495257","doi":"https://doi.org/10.1109/icassp.2012.6288878","title":"Robust speech recognition through selection of speaker and environment transforms","display_name":"Robust speech recognition through selection of speaker and environment transforms","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2117495257","doi":"https://doi.org/10.1109/icassp.2012.6288878","mag":"2117495257"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5059221392","display_name":"Raghavendra Bilgi","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghavendra Bilgi","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras, India","[Department of electrical engineering, Indian Institute of Technology Madras, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of electrical engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019937451","display_name":"Vikas Joshi","orcid":"https://orcid.org/0000-0003-4467-3621"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikas Joshi","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras, India","[Department of electrical engineering, Indian Institute of Technology Madras, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of electrical engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras, India","[Department of electrical engineering, Indian Institute of Technology Madras, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of electrical engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","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":["Dept of Signal Theory, University of Granada, Spain","Dept of Signal Theory, Telematics & Communications. University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Signal Theory, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"Dept of Signal Theory, Telematics & Communications. University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","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":["Dept of Signal Theory, University of Granada, Spain","Dept of Signal Theory, Telematics & Communications. University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Signal Theory, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"Dept of Signal Theory, Telematics & Communications. University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13158155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4333","last_page":"4336"},"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":0.9994000196456909,"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":0.9918000102043152,"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":0.7973525524139404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545328140258789},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7126330733299255},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.683928906917572},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4881897568702698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39953774213790894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32116013765335083}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7973525524139404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545328140258789},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7126330733299255},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.683928906917572},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4881897568702698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39953774213790894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32116013765335083}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W257179395","https://openalex.org/W2002342963","https://openalex.org/W2126597753","https://openalex.org/W2127144047","https://openalex.org/W2135145707","https://openalex.org/W2147143213","https://openalex.org/W2164931619","https://openalex.org/W2168101424","https://openalex.org/W2171000037","https://openalex.org/W2294327763","https://openalex.org/W2406196148","https://openalex.org/W6679972229","https://openalex.org/W6713797532"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1,114],"paper,":[2],"we":[3,83],"address":[4],"the":[5,21,85,92,102,106,143],"problem":[6],"of":[7,23,33,105,145],"robustness":[8],"to":[9,123],"both":[10],"noise":[11,58,94],"and":[12,26,29,113,148,151,165],"speaker-variability":[13],"in":[14],"automatic":[15],"speech":[16],"recognition":[17],"(ASR).":[18],"We":[19],"propose":[20],"use":[22,84],"pre-computed":[24,46,146],"Noise":[25],"Speaker":[27],"transforms,":[28],"an":[30],"optimal":[31],"combination":[32],"these":[34],"two":[35],"transforms":[36,47,71,150],"are":[37,48,61,72],"chosen":[38],"during":[39,50,74,100],"test":[40,159],"using":[41,53,76],"maximum-likelihood":[42],"(ML)":[43],"criterion.":[44],"These":[45],"obtained":[49,55,73],"training":[51,75],"by":[52,117],"data":[54,160],"from":[56],"different":[57],"conditions":[59],"that":[60,65],"usually":[62],"encountered":[63,99],"for":[64,81],"particular":[66],"ASR":[67],"task.":[68,133],"The":[69,134],"environment":[70,95,147],"constrained-MLLR":[77],"(CMLLR)":[78],"framework,":[79],"while":[80],"speaker-transforms":[82],"analytically":[86],"determined":[87],"linear-VTLN":[88],"matrices.":[89],"Even":[90],"though":[91],"exact":[93],"may":[96],"not":[97],"be":[98,154],"test,":[101],"ML-based":[103],"choice":[104,144],"closest":[107],"Environment":[108],"transform":[109],"provides":[110],"\u201csufficient\u201d":[111],"cleaning":[112],"is":[115,137],"corroborated":[116],"experimental":[118],"results":[119],"with":[120,156],"performance":[121],"comparable":[122],"histogram":[124],"equalization":[125],"or":[126],"Vector":[127],"Taylor":[128],"Series":[129],"approaches":[130],"on":[131],"Aurora-2":[132],"proposed":[135],"method":[136],"simple":[138],"since":[139],"it":[140],"involves":[141],"only":[142],"speaker":[149,164],"therefore,":[152],"can":[153],"applied":[155],"very":[157],"little":[158],"unlike":[161],"many":[162],"other":[163],"noise-compensation":[166],"methods.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}