{"id":"https://openalex.org/W1992463165","doi":"https://doi.org/10.1109/tasl.2012.2198058","title":"Vocal Tract Length Normalization for Statistical Parametric Speech Synthesis","display_name":"Vocal Tract Length Normalization for Statistical Parametric Speech Synthesis","publication_year":2012,"publication_date":"2012-06-08","ids":{"openalex":"https://openalex.org/W1992463165","doi":"https://doi.org/10.1109/tasl.2012.2198058","mag":"1992463165"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2198058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2198058","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language 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/192615","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, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","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, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","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, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2193,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95225873,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"7","first_page":"2134","last_page":"2148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.993399977684021,"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":0.7651413679122925},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.740768313407898},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6845618486404419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328241229057312},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5334437489509583},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5083529353141785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3760942220687866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3604239821434021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14384132623672485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651413679122925},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.740768313407898},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6845618486404419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328241229057312},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5334437489509583},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5083529353141785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3760942220687866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3604239821434021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14384132623672485},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":3,"locations":[{"id":"doi:10.1109/tasl.2012.2198058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2198058","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9696","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2012/Saheer_IEEE-TASL_2012.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192615","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192615","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:192615","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192615","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":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2964579","https://openalex.org/W3276882","https://openalex.org/W46300955","https://openalex.org/W70088150","https://openalex.org/W85341942","https://openalex.org/W129295792","https://openalex.org/W164170074","https://openalex.org/W202166873","https://openalex.org/W257179395","https://openalex.org/W1538542060","https://openalex.org/W1724745491","https://openalex.org/W2002342963","https://openalex.org/W2082474452","https://openalex.org/W2115005744","https://openalex.org/W2117418893","https://openalex.org/W2128413412","https://openalex.org/W2129863563","https://openalex.org/W2139246688","https://openalex.org/W2153914468","https://openalex.org/W2164356140","https://openalex.org/W2164931619","https://openalex.org/W2168411176","https://openalex.org/W2169878657","https://openalex.org/W2170120409","https://openalex.org/W2296704011","https://openalex.org/W2397048842","https://openalex.org/W2578760083","https://openalex.org/W3142087749","https://openalex.org/W6605321427","https://openalex.org/W6637620865","https://openalex.org/W6732384642"],"related_works":["https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W2067459736","https://openalex.org/W2020989338","https://openalex.org/W2105635394","https://openalex.org/W2147126679","https://openalex.org/W1823617068","https://openalex.org/W4300049944","https://openalex.org/W2115039802"],"abstract_inverted_index":{"Vocal":[0],"tract":[1],"length":[2],"normalization":[3],"(VTLN)":[4],"has":[5],"been":[6,117],"successfully":[7],"used":[8],"in":[9,22,50,87,92],"automatic":[10],"speech":[11,25,88,96],"recognition":[12],"for":[13,27,53,84,112,135,148],"improved":[14],"performance.":[15],"The":[16,132],"same":[17],"technique":[18,83,106],"can":[19],"be":[20,141],"implemented":[21],"statistical":[23],"parametric":[24],"synthesis":[26,97],"rapid":[28],"speaker":[29],"adaptation":[30],"during":[31],"synthesis.":[32,54,89],"This":[33],"paper":[34],"presents":[35],"an":[36,101],"efficient":[37],"implementation":[38],"of":[39,61,95,143],"VTLN":[40,52,86,91,137],"using":[41,85],"expectation":[42],"maximization":[43],"and":[44,59,123],"addresses":[45],"the":[46,62,71,80,93,105,128,144],"key":[47],"challenges":[48,68],"faced":[49],"implementing":[51,136],"Jacobian":[55],"normalization,":[56],"high-dimensionality":[57],"features":[58,147],"truncation":[60],"transformation":[63],"matrix":[64],"are":[65,76],"a":[66],"few":[67],"presented":[69],"with":[70],"appropriate":[72],"solutions.":[73],"Detailed":[74],"evaluations":[75],"performed":[77],"to":[78,126,140],"estimate":[79],"most":[81],"suitable":[82],"Evaluating":[90],"framework":[94],"is":[98,138],"also":[99],"not":[100,108],"easy":[102],"task":[103],"since":[104],"does":[107],"work":[109],"equally":[110],"well":[111],"all":[113],"speakers.":[114],"Speakers":[115],"have":[116],"selected":[118],"based":[119],"on":[120],"different":[121],"objective":[122],"subjective":[124],"criteria":[125],"demonstrate":[127],"difference":[129],"between":[130],"systems.":[131],"best":[133],"method":[134],"confirmed":[139],"use":[142],"lower":[145],"order":[146],"estimating":[149],"warping":[150],"factors.":[151]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}