{"id":"https://openalex.org/W2001448670","doi":"https://doi.org/10.1109/jstsp.2013.2295554","title":"Combining Vocal Tract Length Normalization With Hierarchical Linear Transformations","display_name":"Combining Vocal Tract Length Normalization With Hierarchical Linear Transformations","publication_year":2014,"publication_date":"2014-01-31","ids":{"openalex":"https://openalex.org/W2001448670","doi":"https://doi.org/10.1109/jstsp.2013.2295554","mag":"2001448670"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2013.2295554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2295554","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017257483","display_name":"Lakshmi Babu Saheer","orcid":"https://orcid.org/0000-0002-5263-596X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lakshmi Saheer","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081808619","display_name":"Philip N. Garner","orcid":"https://orcid.org/0000-0002-0814-1348"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philip N. Garner","raw_affiliation_strings":["Idiap Research Institute, Lausanne, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Lausanne, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["Idiap Research Institute, Lausanne, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Lausanne, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2425,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84255716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":"2","first_page":"262","last_page":"272"},"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":0.9983000159263611,"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":0.9958000183105469,"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":0.7603671550750732},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6918638348579407},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.665267825126648},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6287910342216492},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6160165667533875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.588089108467102},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5217160582542419},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4810474216938019},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4777742624282837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4647476077079773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1772920787334442},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09594666957855225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603671550750732},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6918638348579407},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.665267825126648},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6287910342216492},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6160165667533875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.588089108467102},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5217160582542419},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4810474216938019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4777742624282837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4647476077079773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1772920787334442},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09594666957855225},{"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2013.2295554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2295554","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:192616","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192616","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W70088150","https://openalex.org/W111245198","https://openalex.org/W173010698","https://openalex.org/W571239262","https://openalex.org/W1553129813","https://openalex.org/W1982976845","https://openalex.org/W1992463165","https://openalex.org/W2002342963","https://openalex.org/W2049686551","https://openalex.org/W2081976287","https://openalex.org/W2100340603","https://openalex.org/W2104924374","https://openalex.org/W2114155159","https://openalex.org/W2115005744","https://openalex.org/W2120025343","https://openalex.org/W2129142580","https://openalex.org/W2133035145","https://openalex.org/W2137069988","https://openalex.org/W2139246688","https://openalex.org/W2153914468","https://openalex.org/W2156450495","https://openalex.org/W2158212729","https://openalex.org/W2164931619","https://openalex.org/W2169878657","https://openalex.org/W2296704011","https://openalex.org/W2398317185","https://openalex.org/W3146802053","https://openalex.org/W6607040217","https://openalex.org/W6679574054","https://openalex.org/W6697285287"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W1911592522","https://openalex.org/W2075706796","https://openalex.org/W2087669554","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"demonstrated":[3],"the":[4,43,73,97,105,112,162,181,186,201,216,220,227,234,245,264,278],"effectiveness":[5],"of":[6,30,75,82,188,224,230,257],"vocal":[7],"tract":[8],"length":[9],"normalization":[10],"(VTLN)":[11],"as":[12,96,255],"a":[13,51,88,119,252],"rapid":[14],"adaptation":[15,32,67,86,124,189],"technique":[16,102,133],"for":[17,103,267],"statistical":[18],"parametric":[19],"speech":[20,24,167,247],"synthesis.":[21,258],"VTLN":[22,54,76,93,113,176,211,225],"produces":[23,165],"with":[25,49,80,169,226],"naturalness":[26,171],"preferable":[27],"to":[28,39,63,134,175,180,197,210,261,276],"that":[29,40,72,161,256,263],"MLLR-based":[31],"techniques,":[33],"being":[34],"much":[35],"closer":[36],"in":[37,87,206,212,233,251,274],"quality":[38,168,221],"generated":[41],"by":[42,111],"original":[44],"average":[45],"voice":[46],"model.":[47],"However,":[48],"only":[50],"single":[52],"parameter,":[53],"captures":[55],"very":[56,192],"few":[57],"speaker":[58,199,207,228],"specific":[59],"characteristics":[60],"when":[61,178,185],"compared":[62,179,209],"linear":[64,83,121],"transform":[65,84,114],"based":[66,85],"techniques.":[68,137],"This":[69,127,259],"paper":[70,128],"shows":[71],"merits":[74],"can":[77,269],"be":[78,270],"combined":[79],"those":[81],"hierarchical":[89],"Bayesian":[90],"framework,":[91],"where":[92],"is":[94,125,191,260],"used":[95],"prior":[98],"information.":[99],"A":[100],"novel":[101],"propagating":[104],"gender":[106],"and":[107,144,147,153,172,222,237],"age":[108],"information":[109],"captured":[110],"into":[115,272],"constrained":[116],"structural":[117],"maximum":[118],"posteriori":[120],"regression":[122],"(CSMAPLR)":[123],"presented.":[126],"also":[129,242],"compares":[130],"this":[131],"proposed":[132,202,217],"other":[135],"combination":[136,218],"Experiments":[138,240],"are":[139,241],"performed":[140,243],"on":[141],"both":[142],"matched":[143],"mismatched":[145,235],"training":[146],"test":[148,238],"conditions,":[149],"including":[150],"gender,":[151],"age,":[152],"recording":[154],"environments.":[155],"Text-to-speech":[156],"(TTS)":[157],"synthesis":[158],"experiments":[159],"show":[160],"resulting":[163],"transformation":[164],"improved":[166],"better":[170,205],"intelligibility":[173,223],"(similar":[174],"transformation)":[177],"CSMAPLR":[182,231],"transformation,":[183],"especially":[184,232],"quantity":[187],"data":[190],"limited.":[193],"With":[194],"more":[195],"parameters":[196],"capture":[198],"characteristics,":[200],"method":[203],"performs":[204],"similarity":[208,229],"mis-matched":[213],"conditions.":[214,239],"Hence,":[215],"combines":[219],"train":[236],"using":[244],"automatic":[246],"recognition":[248],"(ASR)":[249],"system":[250],"unified":[253],"framework":[254],"prove":[262],"techniques":[265],"developed":[266],"TTS":[268],"plugged":[271],"ASR":[273],"order":[275],"improve":[277],"performance.":[279]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}