{"id":"https://openalex.org/W2766805498","doi":"https://doi.org/10.23919/eusipco.2017.8081270","title":"VTLN-warped Gaussian posteriorgram for QbE-STD","display_name":"VTLN-warped Gaussian posteriorgram for QbE-STD","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2766805498","doi":"https://doi.org/10.23919/eusipco.2017.8081270","mag":"2766805498"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2017.8081270","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","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/A5048910634","display_name":"Maulik C. Madhavi","orcid":"https://orcid.org/0000-0001-8743-6437"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maulik C. Madhavi","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.6921,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75335128,"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":"563","last_page":"567"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7313337326049805},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7249617576599121},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6335382461547852},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5655586123466492},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.541172981262207},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.49327749013900757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4885185956954956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3759116232395172},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3664909899234772},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19356638193130493},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.18117329478263855},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16943755745887756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313337326049805},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7249617576599121},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6335382461547852},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5655586123466492},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.541172981262207},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.49327749013900757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4885185956954956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759116232395172},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3664909899234772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19356638193130493},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.18117329478263855},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16943755745887756},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2017.8081270","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W103757200","https://openalex.org/W170732776","https://openalex.org/W1557133539","https://openalex.org/W1885329076","https://openalex.org/W1984076147","https://openalex.org/W1998766338","https://openalex.org/W2007463795","https://openalex.org/W2009341345","https://openalex.org/W2048684672","https://openalex.org/W2090861223","https://openalex.org/W2106119541","https://openalex.org/W2109173967","https://openalex.org/W2126203737","https://openalex.org/W2137044559","https://openalex.org/W2140956445","https://openalex.org/W2148154194","https://openalex.org/W2154093685","https://openalex.org/W2164365067","https://openalex.org/W2164931619","https://openalex.org/W2170679724","https://openalex.org/W2171019095","https://openalex.org/W2400268965"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W2077224612","https://openalex.org/W2153481672","https://openalex.org/W2153238387","https://openalex.org/W4312864369","https://openalex.org/W84255947","https://openalex.org/W2014842417","https://openalex.org/W2891133681","https://openalex.org/W2061347451"],"abstract_inverted_index":{"Vocal":[0],"Tract":[1],"Length":[2],"Normalization":[3],"(VTLN)":[4],"is":[5,150],"a":[6,31,43,117,128],"very":[7],"important":[8],"speaker":[9],"normalization":[10],"technique":[11],"for":[12,30,49,69,77],"speech":[13],"recognition":[14],"tasks.":[15,71],"In":[16],"this":[17],"paper,":[18],"we":[19],"propose":[20,73],"the":[21,40,74,100,141],"use":[22,41],"of":[23,26,42,51,106,119,130],"Gaussian":[24,44,97,120,138,145,157],"posteriorgram":[25,98,139,146],"VTLN-warped":[27,96,137],"spectral":[28],"features":[29],"Query-by-Example":[32],"Spoken":[33],"Term":[34],"Detection":[35],"(QbE-STD).":[36],"This":[37,55],"paper":[38],"presents":[39],"Mixture":[45],"Model":[46],"(GMM)":[47],"framework":[48,57],"estimation":[50,81],"VTLN":[52,78,133],"warping":[53,79,134],"factor.":[54],"GMM":[56,84],"does":[58],"not":[59],"require":[60],"phoneme-level":[61],"transcription":[62],"and":[63,90,127,147],"hence,":[64,148],"it":[65,149],"can":[66],"be":[67],"useful":[68],"unsupervised":[70],"We":[72],"iterative":[75],"approach":[76],"factor":[80,135],"with":[82,111],"two":[83],"training":[85],"approaches,":[86],"namely,":[87],"Expectation-Maximization":[88],"(EM)":[89],"Deterministic":[91],"Annealing-Expectation":[92],"Maximization":[93],"(DAEM).":[94],"The":[95,104],"gave":[99],"better":[101,154],"QbE-STD":[102,108],"performance.":[103],"performance":[105,155],"TIMIT":[107],"was":[109],"investigated":[110],"different":[112],"evaluation":[113],"factors,":[114],"such":[115],"as":[116],"number":[118,129],"components":[121],"in":[122,132,144],"GMM,":[123],"various":[124],"local":[125],"constraints,":[126],"iterations":[131],"estimation.":[136],"reduces":[140],"speaker-specific":[142],"variation":[143],"expected":[151],"to":[152],"give":[153],"than":[156],"posteriorgram.":[158]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}