{"id":"https://openalex.org/W159433267","doi":"https://doi.org/10.21437/interspeech.2009-200","title":"Speaker normalization for template based speech recognition","display_name":"Speaker normalization for template based speech recognition","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W159433267","doi":"https://doi.org/10.21437/interspeech.2009-200","mag":"159433267"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5069817284","display_name":"S\u00e9bastien Demange","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Demange","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041039488","display_name":"Dirk Van Compernolle","orcid":"https://orcid.org/0000-0003-0075-848X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dirk Van Compernolle","raw_affiliation_strings":["Katholieke Universiteit \u00adLeuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Katholieke Universiteit \u00adLeuven","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.453,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70941395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"560","last_page":"563"},"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":0.9990000128746033,"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":0.9980999827384949,"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":0.8971054553985596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966150045394897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7886565923690796},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.7318721413612366},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6896602511405945},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.661320149898529},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6118350625038147},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5147252082824707},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.5091893076896667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43724825978279114},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42726975679397583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3926222324371338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35215699672698975},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11185911297798157}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8971054553985596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966150045394897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7886565923690796},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.7318721413612366},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6896602511405945},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.661320149898529},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6118350625038147},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5147252082824707},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.5091893076896667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43724825978279114},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42726975679397583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3926222324371338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35215699672698975},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11185911297798157},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2009-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.2021","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.2021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00583853v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00583853","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th Annual Conference of the International Speech Communication Association - Interspeech 2009, Sep 2009, Brighton, United Kingdom. pp.560--563","raw_type":"Conference papers"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/243049","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/243049/2/2900.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech2009 - 10th annual conference of the international speech communication association, Brighton, UK, 6-10 September 2009","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6200000047683716,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W189143427","https://openalex.org/W1746705224","https://openalex.org/W2097207027","https://openalex.org/W2147542668","https://openalex.org/W2521148661"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2740630172","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Vocal":[0],"Tract":[1],"Length":[2],"Normalization":[3],"(VTLN)":[4],"has":[5],"been":[6],"shown":[7],"to":[8,70,92,97,111],"be":[9],"an":[10],"efficient":[11,28],"speaker":[12,62,126],"normalization":[13],"tool":[14],"for":[15,29],"HMM":[16],"based":[17,32,36,123],"systems.":[18],"In":[19,101],"this":[20,109],"paper":[21],"we":[22],"show":[23,79],"that":[24,44,80],"it":[25],"is":[26],"equally":[27],"a":[30,71,112],"template":[31,122],"recognition":[33],"system.":[34],"Template":[35],"systems,":[37],"while":[38],"promising,":[39],"have":[40],"as":[41],"potential":[42],"drawback":[43],"templates":[45,91],"maintain":[46],"all":[47],"non":[48],"phonetic":[49],"details":[50],"apart":[51],"from":[52,87],"the":[53,76,93,98,104],"essential":[54],"phonemic":[55],"properties;":[56],"i.e.":[57],"they":[58],"retain":[59],"information":[60],"on":[61,103],"and":[63],"acoustic":[64],"recording":[65],"circumstances.":[66],"This":[67],"may":[68],"lead":[69],"very":[72],"inefficient":[73],"usage":[74],"of":[75,118],"database.":[77],"We":[78],"after":[81],"VTLN":[82],"significantly":[83],"more":[84],"speakers-":[85],"also":[86],"opposite":[88],"gender-":[89],"contribute":[90],"matching":[94],"sequence":[95],"compared":[96],"non-normalized":[99],"case.":[100],"experiments":[102],"Wall":[105],"Street":[106],"Journal":[107],"database":[108],"leads":[110],"relative":[113],"word":[114],"error":[115],"rate":[116],"reduction":[117],"10%.":[119],"Index":[120],"Terms:":[121],"speech":[124],"recognition,":[125],"normalization,":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}