{"id":"https://openalex.org/W2000724074","doi":"https://doi.org/10.1109/asru.2013.6707722","title":"Improved cepstral mean and variance normalization using Bayesian framework","display_name":"Improved cepstral mean and variance normalization using Bayesian framework","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2000724074","doi":"https://doi.org/10.1109/asru.2013.6707722","mag":"2000724074"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047027367","display_name":"Nitin Prasad","orcid":"https://orcid.org/0000-0001-8088-0164"},"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":"N. Vishnu Prasad","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras, India","[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, 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":"[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","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","[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, 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":"[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":3.2033,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.93220594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"161"},"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":0.9998000264167786,"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":0.9955999851226807,"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":0.850739598274231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348340511322021},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6346480846405029},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.5461283326148987},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5459077954292297},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5108897089958191},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.45539161562919617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45518726110458374},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4481833279132843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39327874779701233},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3572978973388672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2590871751308441},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.12567421793937683}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.850739598274231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348340511322021},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6346480846405029},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.5461283326148987},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5459077954292297},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5108897089958191},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.45539161562919617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45518726110458374},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4481833279132843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39327874779701233},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3572978973388672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2590871751308441},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.12567421793937683},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/asru.2013.6707722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W90966543","https://openalex.org/W144317751","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2080921589","https://openalex.org/W2105885996","https://openalex.org/W2126597753","https://openalex.org/W2137737117","https://openalex.org/W2151484683","https://openalex.org/W2171000037","https://openalex.org/W2404450935","https://openalex.org/W6670794517","https://openalex.org/W6682194319","https://openalex.org/W6713794348"],"related_works":["https://openalex.org/W2144521324","https://openalex.org/W289005589","https://openalex.org/W2047769394","https://openalex.org/W1608910676","https://openalex.org/W2153557281","https://openalex.org/W2625954004","https://openalex.org/W2155082225","https://openalex.org/W3104006473","https://openalex.org/W2594616939","https://openalex.org/W3209142031"],"abstract_inverted_index":{"Cepstral":[0,115],"Mean":[1,116],"and":[2,35,49,63,119,126,138,147,151],"Variance":[3],"Normalization":[4],"(CMVN)":[5],"is":[6,21,85],"a":[7,80],"computationally":[8],"efficient":[9],"normalization":[10],"technique":[11],"for":[12,25,32,101,132,144],"noise":[13],"robust":[14,81],"speech":[15],"recognition.":[16],"The":[17,107],"performance":[18],"of":[19,37,61,68,83,111],"CMVN":[20,118],"known":[22],"to":[23,29,45,57,78,88],"degrade":[24],"short":[26,145],"utterances,":[27,134,146],"due":[28],"insufficient":[30],"data":[31],"parameter":[33],"estimation":[34],"loss":[36],"discriminable":[38,90],"information":[39,91],"as":[40],"all":[41,133],"utterances":[42],"are":[43,122],"forced":[44],"have":[46],"zero":[47],"mean":[48,62],"unit":[50],"variance.":[51],"In":[52],"this":[53,112],"work,":[54],"we":[55],"propose":[56],"use":[58],"posterior":[59],"estimates":[60],"variance":[64],"in":[65,76,94],"CMVN,":[66],"instead":[67],"the":[69,129,141,154],"maximum":[70],"likelihood":[71],"estimates.":[72],"This":[73],"Bayesian":[74],"approach,":[75],"addition":[77],"providing":[79],"estimate":[82],"parameters,":[84],"also":[86],"shown":[87],"preserve":[89],"without":[92],"increase":[93],"computational":[95],"cost,":[96],"making":[97],"it":[98],"particularly":[99],"relevant":[100],"Interactive":[102],"Voice":[103],"Response":[104],"(IVR)-based":[105],"applications.":[106],"relative":[108],"WER":[109],"reduction":[110],"approach":[113],"w.r.t.":[114],"Normalization,":[117],"Histogram":[120],"Equalization":[121],"(i)":[123],"40.1%,":[124],"27%":[125],"4.3%":[127],"with":[128,140,153],"Aurora2":[130,142],"database":[131,143],"(ii)":[135],"25.7%,":[136],"38.6%":[137],"30.4%":[139],"(iii)":[148],"18.7%,":[149],"12.6%":[150],"2.5%":[152],"Aurora4":[155],"database.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}