{"id":"https://openalex.org/W2123771434","doi":"https://doi.org/10.1109/fskd.2007.347","title":"High Quality Voice Conversion through Phoneme-Based Linear Mapping Functions with STRAIGHT for Mandarin","display_name":"High Quality Voice Conversion through Phoneme-Based Linear Mapping Functions with STRAIGHT for Mandarin","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2123771434","doi":"https://doi.org/10.1109/fskd.2007.347","mag":"2123771434"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2007.347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2007.347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007)","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/A5100398807","display_name":"Kun Liu","orcid":"https://orcid.org/0000-0003-3074-7167"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Liu","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","[Chinese Acad. of Sci, Beijing]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"[Chinese Acad. of Sci, Beijing]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390066","display_name":"Jianping Zhang","orcid":"https://orcid.org/0000-0001-7141-9464"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","[Chinese Acad. of Sci, Beijing]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"[Chinese Acad. of Sci, Beijing]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","[Chinese Acad. of Sci, Beijing]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"[Chinese Acad. of Sci, Beijing]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":1.1128,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.78459362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980999827384949,"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":0.993399977684021,"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/speech-recognition","display_name":"Speech recognition","score":0.7944144010543823},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7750434279441833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6878129243850708},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6835319399833679},{"id":"https://openalex.org/keywords/abx-test","display_name":"ABX test","score":0.6671594977378845},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6450631618499756},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6176702976226807},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5736534595489502},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5651906728744507},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4931945204734802},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44576844573020935},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4126286208629608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3080274164676666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2118198275566101},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.08172279596328735}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7944144010543823},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7750434279441833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878129243850708},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6835319399833679},{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.6671594977378845},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6450631618499756},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6176702976226807},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5736534595489502},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5651906728744507},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4931945204734802},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44576844573020935},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4126286208629608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3080274164676666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2118198275566101},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.08172279596328735},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2007.347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2007.347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W62664237","https://openalex.org/W108550785","https://openalex.org/W173492274","https://openalex.org/W196920580","https://openalex.org/W1483144309","https://openalex.org/W1526513105","https://openalex.org/W1592940279","https://openalex.org/W1926768285","https://openalex.org/W1963778986","https://openalex.org/W2013996527","https://openalex.org/W2067234399","https://openalex.org/W2096555739","https://openalex.org/W2096564043","https://openalex.org/W2105698384","https://openalex.org/W2110589840","https://openalex.org/W2111550316","https://openalex.org/W2114543868","https://openalex.org/W2118850452","https://openalex.org/W2123003832","https://openalex.org/W2136166660","https://openalex.org/W2139056654","https://openalex.org/W2156142001","https://openalex.org/W2341580134","https://openalex.org/W2405069075","https://openalex.org/W6604322312","https://openalex.org/W6608098027","https://openalex.org/W6653852971","https://openalex.org/W6676465519","https://openalex.org/W6704437622"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2025848302","https://openalex.org/W2045900265"],"abstract_inverted_index":{"A":[0],"novel":[1],"voice":[2,20,145],"conversion":[3,21,136],"system":[4],"using":[5,31,92],"phoneme-based":[6,58],"linear":[7,62],"mapping":[8,63,71],"functions":[9,64],"on":[10,124],"main":[11,87],"vowel":[12,88],"phonemes":[13,89],"is":[14,106,146],"proposed":[15],"in":[16,39,77,170],"this":[17,171],"paper.":[18,172],"Our":[19],"algorithm":[22],"has":[23],"the":[24,33,40,47,51,70,78,81,86,93,103,109,143],"following":[25],"three":[26],"improvements.":[27],"First,":[28],"instead":[29],"of":[30,42,53,127,142],"all":[32],"vocal":[34],"tract":[35],"resonance":[36],"(VTR)":[37],"vectors":[38],"portion":[41],"a":[43],"phoneme,":[44],"we":[45],"use":[46],"VTR":[48],"vector":[49],"at":[50,85],"steady-state":[52],"each":[54],"phoneme":[55],"to":[56,68,150,157],"train":[57],"GMM.":[59,95],"Second,":[60],"different":[61],"have":[65],"been":[66],"trained":[67],"describe":[69],"relationships":[72],"for":[73,132],"corresponding":[74,94],"phonemes.":[75],"Third,":[76],"transformation":[79],"procedure,":[80],"transformed":[82,110],"formant":[83],"frequencies":[84],"are":[90,99,167],"obtained":[91],"Besides,":[96],"prosody":[97],"parameters":[98,111],"also":[100,168],"transformed.":[101],"Finally":[102],"converted":[104,144],"speech":[105,115],"re-synthesized":[107],"with":[108,160,164],"by":[112],"high":[113],"quality":[114],"manipulation":[116],"framework":[117],"STRAIGHT":[118],"(Speech":[119],"Transformation":[120],"and":[121,134,152],"Representation":[122],"based":[123],"Adaptive":[125],"Interpolation":[126],"weiGHTed":[128],"spectrogram).":[129],"Perceptual":[130],"results":[131],"F-M":[133],"M-F":[135],"show":[137],"that":[138],"our":[139],"MOS":[140],"score":[141,154],"improved":[147],"from":[148,155],"3.8":[149,158],"4.1":[151],"ABX":[153],"3.3":[156],"compared":[159],"IBM's":[161],"system.":[162],"Comparisons":[163],"other":[165],"systems":[166],"given":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}