{"id":"https://openalex.org/W2403098732","doi":"https://doi.org/10.21437/interspeech.2014-363","title":"Voice expression conversion with factorised HMM-TTS models","display_name":"Voice expression conversion with factorised HMM-TTS models","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2403098732","doi":"https://doi.org/10.21437/interspeech.2014-363","mag":"2403098732"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031222393","display_name":"Vincent Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1514","last_page":"1518"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/expression","display_name":"Expression (computer science)","score":0.8412494659423828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7358745336532593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.723397970199585},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.7227447032928467},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6645913124084473},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6318753957748413},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5640442967414856},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5042136907577515},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49211281538009644},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4758284389972687},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4257586598396301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893585801124573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38042330741882324},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0886564552783966}],"concepts":[{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.8412494659423828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7358745336532593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723397970199585},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.7227447032928467},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6645913124084473},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6318753957748413},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5640442967414856},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5042136907577515},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49211281538009644},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4758284389972687},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4257586598396301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893585801124573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38042330741882324},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0886564552783966},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W87461617","https://openalex.org/W92302539","https://openalex.org/W113106864","https://openalex.org/W126988493","https://openalex.org/W170432670","https://openalex.org/W179271164","https://openalex.org/W1523817494","https://openalex.org/W1588037970","https://openalex.org/W1590015269","https://openalex.org/W1596263485","https://openalex.org/W1931958196","https://openalex.org/W1935012542","https://openalex.org/W2000397476","https://openalex.org/W2009396100","https://openalex.org/W2025638820","https://openalex.org/W2042946036","https://openalex.org/W2067175291","https://openalex.org/W2088163323","https://openalex.org/W2100351502","https://openalex.org/W2114543868","https://openalex.org/W2114659828","https://openalex.org/W2118850452","https://openalex.org/W2129360799","https://openalex.org/W2145130307","https://openalex.org/W2148846882","https://openalex.org/W2150791533","https://openalex.org/W2153057929","https://openalex.org/W2158197208","https://openalex.org/W2161736993","https://openalex.org/W2179117922","https://openalex.org/W2407110532"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,24,126],"method":[4,22,114],"to":[5,92,97,101,119],"modify":[6,98],"the":[7,18,30,41,48,53,64,68,76,93,102,107,110,123],"expression":[8,51,65,70,78,86,100],"or":[9],"emotion":[10],"in":[11],"sample":[13,56,96],"of":[14,43,52,67,109],"speech":[15,26,55,95],"without":[16,105,122],"altering":[17,106],"speaker\u2019s":[19],"identity.":[20],"The":[21],"exploits":[23],"statistical":[25],"model":[27],"that":[28,45],"factorises":[29],"speaker":[31,49],"identity":[32,108],"from":[33,72],"expressions":[34],"using":[35],"linear":[36],"transforms.":[37],"For":[38],"this":[39,113],"approach,":[40],"set":[42],"transforms":[44,66],"best":[46],"fit":[47],"and":[50,82],"input":[54],"are":[57,60],"learned.":[58],"They":[59],"then":[61],"combined":[62,77],"with":[63],"desired":[69,103],"taken":[71],"another":[73],"speaker.":[74,111],"Since":[75],"transform":[79],"is":[80],"factorised":[81],"contains":[83],"information":[84],"about":[85],"only,":[87],"it":[88],"may":[89,115],"be":[90,116],"applied":[91,117],"original":[94],"its":[99],"one":[104],"Notably,":[112],"universally":[118],"any":[120],"voice":[121],"need":[124],"for":[125],"parallel":[127],"training":[128],"corpus.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}