{"id":"https://openalex.org/W2290946177","doi":"https://doi.org/10.1109/apsipa.2015.7415320","title":"Mapping frames with DNN-HMM recognizer for non-parallel voice conversion","display_name":"Mapping frames with DNN-HMM recognizer for non-parallel voice conversion","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2290946177","doi":"https://doi.org/10.1109/apsipa.2015.7415320","mag":"2290946177"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},"type":"article","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/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678003","display_name":"Chenyu Yang","orcid":"https://orcid.org/0000-0001-9997-4929"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenyu Yang","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112223666","display_name":"Yanfeng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yanfeng Lu","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060496850","display_name":"Jochen Ehnes","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jochen Walter Ehnes","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112133862","display_name":"Dongyan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110320609","display_name":"Huaiping Ming","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huaiping Ming","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055221016","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0003-3410-8354"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049491887","display_name":"Siu Wa Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siu Wa Lee","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A-Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1162,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93112955,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"22","issue":null,"first_page":"488","last_page":"494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9926000237464905,"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":0.8382251262664795},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7904829382896423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7223443984985352},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6699696779251099},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6336785554885864},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6076235771179199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5046271085739136},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49481815099716187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48487719893455505},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4594043791294098},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45378419756889343},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.315868079662323},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10819509625434875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382251262664795},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7904829382896423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7223443984985352},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6699696779251099},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6336785554885864},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6076235771179199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5046271085739136},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49481815099716187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48487719893455505},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4594043791294098},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45378419756889343},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.315868079662323},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10819509625434875},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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":39,"referenced_works":["https://openalex.org/W33829787","https://openalex.org/W49412823","https://openalex.org/W95152782","https://openalex.org/W1520370180","https://openalex.org/W1524333225","https://openalex.org/W1526513105","https://openalex.org/W1547849677","https://openalex.org/W1588266896","https://openalex.org/W1977362459","https://openalex.org/W2011916518","https://openalex.org/W2017425464","https://openalex.org/W2067175291","https://openalex.org/W2067234399","https://openalex.org/W2105160541","https://openalex.org/W2110584444","https://openalex.org/W2114543868","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2135029798","https://openalex.org/W2136166660","https://openalex.org/W2144294430","https://openalex.org/W2152974894","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2169579015","https://openalex.org/W2185573909","https://openalex.org/W2577042574","https://openalex.org/W3143596294","https://openalex.org/W6601306257","https://openalex.org/W6602007935","https://openalex.org/W6603838645","https://openalex.org/W6631362777","https://openalex.org/W6635216677","https://openalex.org/W6680012447","https://openalex.org/W6732251480"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W2182848507","https://openalex.org/W101156158","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2387825067"],"abstract_inverted_index":{"To":[0],"convert":[1],"one":[2],"speaker's":[3],"voice":[4,26,145],"to":[5,17,36,64,69,88,109,120,143],"another's,":[6],"the":[7,10,51,90,99,102,127,134],"mapping":[8,54,117],"of":[9,39,82],"corresponding":[11],"speech":[12,49,78],"segments":[13],"from":[14,118],"source":[15,40,75,112,119],"speaker":[16,19],"target":[18,42,77,114,121],"must":[20],"be":[21],"obtained":[22],"first.":[23],"In":[24,59],"parallel":[25,144],"conversion,":[27],"normally":[28],"dynamic":[29],"time":[30],"warping":[31],"(DTW)":[32],"method":[33,55,106,136],"is":[34,85,96,107,122],"used":[35,87,108],"align":[37],"signals":[38],"and":[41,76,113],"voices.":[43],"However,":[44],"for":[45,73],"conversion":[46,140],"between":[47,93,101],"non-parallel":[48],"data,":[50],"DTW":[52],"based":[53,125],"does":[56],"not":[57],"work.":[58],"this":[60],"paper,":[61],"we":[62],"propose":[63],"use":[65],"a":[66],"DNN-HMM":[67],"recognizer":[68],"recognize":[70],"each":[71],"frame":[72],"both":[74,111],"signals.":[79],"The":[80,130],"vector":[81],"pseudo":[83],"likelihood":[84],"then":[86,123],"represent":[89],"frame.":[91],"Similarity":[92],"two":[94],"frames":[95],"measured":[97],"with":[98],"distance":[100],"vectors.":[103],"A":[104],"clustering":[105,128],"group":[110],"frames.":[115],"Frame":[116],"established":[124],"on":[126],"result.":[129],"experiments":[131],"show":[132],"that":[133],"proposed":[135],"can":[137],"generate":[138],"similar":[139],"results":[141],"compared":[142],"conversion.":[146]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}