{"id":"https://openalex.org/W50457503","doi":"https://doi.org/10.21437/eurospeech.2003-194","title":"Estimation of GMM in voice conversion including unaligned data","display_name":"Estimation of GMM in voice conversion including unaligned data","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W50457503","doi":"https://doi.org/10.21437/eurospeech.2003-194","mag":"50457503"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5058383534","display_name":"Helenca Duxans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helenca Duxans","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"861","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9923999905586243,"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":0.9728000164031982,"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":0.807998776435852},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7602555751800537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7032362818717957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5678623914718628},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5411592721939087},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.4687006175518036},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.44630828499794006},{"id":"https://openalex.org/keywords/data-conversion","display_name":"Data conversion","score":0.4360455274581909},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4325904846191406},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.41794946789741516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3823360204696655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15403532981872559},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0720587968826294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807998776435852},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7602555751800537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032362818717957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5678623914718628},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5411592721939087},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.4687006175518036},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.44630828499794006},{"id":"https://openalex.org/C1232282","wikidata":"https://www.wikidata.org/wiki/Q1783551","display_name":"Data conversion","level":2,"score":0.4360455274581909},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4325904846191406},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.41794946789741516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3823360204696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15403532981872559},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0720587968826294},{"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},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1570450547","https://openalex.org/W1574649457","https://openalex.org/W2118850452","https://openalex.org/W2123003832","https://openalex.org/W2137054688"],"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/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,20,75,111],"consists":[2],"in":[3,102,126],"transforming":[4],"a":[5,10,56,106,109,118],"source":[6,30,42,82,100,136],"speaker":[7,12,31,35,137],"voice":[8,19,74,110,143],"into":[9],"target":[11,34,60,88],"voice.":[13],"There":[14],"are":[15,70,95,124],"many":[16],"applications":[17],"of":[18,25,41,59,105,121,141],"systems":[21],"where":[22],"the":[23,29,33,39,53,103,127,135,139,142],"amount":[24,40,58,120],"training":[26,128],"data":[27,43,83,101,133],"from":[28,134],"and":[32],"is":[36,45,49,114],"different.":[37],"Usually,":[38],"available":[44,125],"large,":[46],"but":[47,77],"it":[48],"desired":[50],"to":[51,73,97,130],"estimate":[52],"transformation":[54],"with":[55,81],"small":[57],"data.":[61,89],"Systems":[62],"based":[63],"on":[64],"joint":[65],"Gaussian":[66],"Mixture":[67],"Models":[68],"(GMM)":[69],"well":[71],"suited":[72],"[1],":[76],"they":[78],"can\u2019t":[79],"deal":[80],"without":[84],"its":[85],"corresponding":[86],"aligned":[87,122],"In":[90],"this":[91],"paper,":[92],"two":[93],"alternatives":[94],"studied":[96],"incorporate":[98],"unaligned":[99],"estimation":[104],"GMM":[107],"for":[108],"task.":[112],"It":[113],"shown":[115],"that":[116],"when":[117],"limited":[119],"parameters":[123],"step,":[129],"only":[131],"include":[132],"increases":[138],"performance":[140],"transformation.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
