{"id":"https://openalex.org/W100838754","doi":"https://doi.org/10.21437/interspeech.2009-487","title":"Efficient modeling of temporal structure of speech for applications in voice transformation","display_name":"Efficient modeling of temporal structure of speech for applications in voice transformation","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W100838754","doi":"https://doi.org/10.21437/interspeech.2009-487","mag":"100838754"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-487","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":true,"oa_status":"green","oa_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/9982/1/IS2009_Binh.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091142923","display_name":"Binh P. Nguyen","orcid":"https://orcid.org/0000-0001-6203-6664"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Binh Phu Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi Shi, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi Shi, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091142923"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9033,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79006193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1631","last_page":"1634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9810000061988831,"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":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758923172950745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6200647950172424},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5833308100700378},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42831045389175415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758923172950745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6200647950172424},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5833308100700378},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42831045389175415},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-487","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:irdb.nii.ac.jp:01333:0002023419","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/9982","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/9982/1/IS2009_Binh.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of INTERSPEECH 2009","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01333:0002023419","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/9982","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/9982/1/IS2009_Binh.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of INTERSPEECH 2009","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W100838754.pdf","grobid_xml":"https://content.openalex.org/works/W100838754.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Aims":[0],"of":[1,8,51,62,65,71,79,93,114,130,152,156,160],"voice":[2,12,84,145],"transformation":[3,13],"are":[4,43],"to":[5,48,67,110,120,126],"change":[6],"styles":[7],"given":[9],"utterances.":[10],"Most":[11],"methods":[14,30],"process":[15],"speech":[16,54,66,74,81,102,141],"signals":[17],"in":[18,82,137,154],"a":[19,59,101],"time-frequency":[20],"domain.":[21],"In":[22,86],"the":[23,49,52,69,72,77,83,94,122,128,135,150,158,161],"time":[24],"domain,":[25],"whenprocessing":[26],"spectral":[27,123,144],"information,":[28],"conventional":[29],"do":[31],"not":[32],"consider":[33],"relations":[34],"between":[35,45],"neighboring":[36],"frames.":[37],"If":[38],"unexpected":[39],"modifications":[40],"happen,":[41],"there":[42],"discontinuities":[44],"frames,which":[46],"lead":[47],"degradation":[50],"transformed":[53,73,80,131,162],"quality.":[55],"This":[56],"paper":[57],"proposes":[58],"new":[60],"modeling":[61],"temporal":[63,95,112],"structure":[64,113],"ensure":[68,127],"smoothness":[70,129],"for":[75],"improving":[76,157],"quality":[78,159],"transformation.":[85],"our":[87],"work,":[88],"we":[89],"propose":[90],"an":[91],"improvement":[92],"decomposition":[96],"(TD)":[97],"technique,":[98],"which":[99],"decomposes":[100],"signal":[103],"into":[104],"event":[105,108],"targets":[106],"and":[107,125,143],"functions,":[109],"modelthe":[111],"speech.":[115,132,163],"The":[116],"TD":[117,136,153],"is":[118],"used":[119],"control":[121],"dynamics":[124],"We":[133],"investigate":[134],"two":[138],"applications,":[139],"concatenative":[140],"synthesis":[142],"conversion.":[146],"Experimental":[147],"results":[148],"confirm":[149],"effectiveness":[151],"terms":[155]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
