{"id":"https://openalex.org/W1562777581","doi":"https://doi.org/10.1109/icassp.2015.7178897","title":"AA spectral space warping approach to cross-lingual voice transformation in HMM-based TTS","display_name":"AA spectral space warping approach to cross-lingual voice transformation in HMM-based TTS","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1562777581","doi":"https://doi.org/10.1109/icassp.2015.7178897","mag":"1562777581"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088544652","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-1695-8825"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","Speech Group, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Speech Group, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.411,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.55802954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4874","last_page":"4878"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9886000156402588,"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":0.9801999926567078,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7534092664718628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261941432952881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7028828859329224},{"id":"https://openalex.org/keywords/spectral-space","display_name":"Spectral space","score":0.700351893901825},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6708211898803711},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5468258261680603},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5361853241920471},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5277382135391235},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4378199875354767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3982352614402771},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21290582418441772},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18265050649642944}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7534092664718628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261941432952881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7028828859329224},{"id":"https://openalex.org/C2778740170","wikidata":"https://www.wikidata.org/wiki/Q7575210","display_name":"Spectral space","level":2,"score":0.700351893901825},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6708211898803711},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5468258261680603},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5361853241920471},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5277382135391235},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4378199875354767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3982352614402771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21290582418441772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18265050649642944},{"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329815","display_name":"Hong Kong Government","ror":"https://ror.org/034179816"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W2016010921","https://openalex.org/W2093450784","https://openalex.org/W2102504831","https://openalex.org/W2114010348","https://openalex.org/W2115005744","https://openalex.org/W2123808477","https://openalex.org/W2141461755","https://openalex.org/W2154920538","https://openalex.org/W2169878657","https://openalex.org/W2222512263","https://openalex.org/W2395500689"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W1992908141","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0,136],"paper":[1],"presents":[2],"a":[3,145],"new":[4,146],"approach":[5,62],"to":[6,30,47,72,109],"cross-lingual":[7],"voice":[8,131],"transformation":[9],"in":[10,21,35,58,97,112,132],"HMM-based":[11],"TTS":[12,147],"with":[13],"only":[14],"the":[15,36,41,65,69,74,88,93,98,102,113,117,127,133],"recordings":[16],"from":[17],"two":[18,70,89],"monolingual":[19,129],"speakers":[20,71],"different":[22,59],"languages":[23],"(e.g.":[24],"Mandarin":[25],"and":[26],"English).":[27],"We":[28,39],"aim":[29],"synthesize":[31,123],"one":[32],"speaker's":[33,130],"speech":[34,57,95,125],"other":[37,134],"language.":[38,135],"regard":[40],"spectral":[42,66,90,99,114],"space":[43,100,115],"of":[44,50,56,68,77,101,116],"any":[45],"speaker":[46,104],"be":[48,106,139],"composed":[49],"universal":[51],"elementary":[52],"units":[53],"(i.e.":[54],"tied-states)":[55],"languages.":[60],"Our":[61],"first":[63],"forces":[64],"spaces":[67],"have":[73],"same":[75],"number":[76],"tied-states.":[78],"Then":[79],"we":[80,121],"find":[81],"an":[82],"optimal":[83],"one-to-one":[84],"tied-state":[85],"mapping":[86],"between":[87],"spaces.":[91],"Hence,":[92],"mapped":[94],"trajectory":[96],"target":[103,128],"can":[105,122,137],"found":[107],"according":[108],"that":[110],"generated":[111],"reference":[118],"speaker.":[119],"Consequently,":[120],"high-quality":[124],"for":[126,144],"also":[138],"used":[140],"as":[141],"training":[142],"data":[143],"system.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
