{"id":"https://openalex.org/W2115747813","doi":"https://doi.org/10.1109/icassp.2004.1325912","title":"Voice conversion through transformation of spectral and intonation features","display_name":"Voice conversion through transformation of spectral and intonation features","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2115747813","doi":"https://doi.org/10.1109/icassp.2004.1325912","mag":"2115747813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5001344814","display_name":"Dimitrios Rentzos","orcid":null},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]},{"id":"https://openalex.org/I60488453","display_name":"Middlesex University","ror":"https://ror.org/01rv4p989","country_code":"GB","type":"education","lineage":["https://openalex.org/I60488453"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"D. Rentzos","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","institution_ids":["https://openalex.org/I60488453"]},{"raw_affiliation_string":"Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109547430","display_name":"Saeed V. Vaseghi","orcid":null},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]},{"id":"https://openalex.org/I60488453","display_name":"Middlesex University","ror":"https://ror.org/01rv4p989","country_code":"GB","type":"education","lineage":["https://openalex.org/I60488453"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. Vaseghi","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","institution_ids":["https://openalex.org/I60488453"]},{"raw_affiliation_string":"Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064860911","display_name":"Yan Qin","orcid":"https://orcid.org/0000-0002-4184-9022"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]},{"id":"https://openalex.org/I60488453","display_name":"Middlesex University","ror":"https://ror.org/01rv4p989","country_code":"GB","type":"education","lineage":["https://openalex.org/I60488453"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qin Yan","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Brunei University, Middlesex, UK","institution_ids":["https://openalex.org/I60488453"]},{"raw_affiliation_string":"Dept. of Electron. & Comput. Eng., Brunel Univ., Uxbridge, UK","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110204490","display_name":"Ching-Hsiang Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I160272722","display_name":"Fortune Institute of Technology","ror":"https://ror.org/036fkkq18","country_code":"TW","type":"education","lineage":["https://openalex.org/I160272722"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Hsiang Ho","raw_affiliation_strings":["Fortune Institute of Technology, Kaohsiung, Taiwan","[Fortune Institute of Technology, Kaohsiung, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fortune Institute of Technology, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I160272722"]},{"raw_affiliation_string":"[Fortune Institute of Technology, Kaohsiung, Taiwan]","institution_ids":["https://openalex.org/I160272722"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.12658872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.9927999973297119,"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/formant","display_name":"Formant","score":0.9253619313240051},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.819904625415802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7401299476623535},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7299156785011292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6317715644836426},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.5232088565826416},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4670521020889282},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44566312432289124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3260475993156433},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11428654193878174},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.09473448991775513}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9253619313240051},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.819904625415802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7401299476623535},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7299156785011292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6317715644836426},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.5232088565826416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4670521020889282},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44566312432289124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3260475993156433},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11428654193878174},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.09473448991775513},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1325912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1526513105","https://openalex.org/W1594223010","https://openalex.org/W1974555773","https://openalex.org/W2109247442","https://openalex.org/W2118850452","https://openalex.org/W2989910616","https://openalex.org/W6676376841"],"related_works":["https://openalex.org/W2611973037","https://openalex.org/W1607387412","https://openalex.org/W2150511655","https://openalex.org/W2005059380","https://openalex.org/W2142042197","https://openalex.org/W2094092160","https://openalex.org/W1922498538","https://openalex.org/W3158918377","https://openalex.org/W2171765479","https://openalex.org/W1520688545"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,19,64],"voice":[4,52,133],"conversion":[5],"method":[6,106],"based":[7,105],"on":[8,82],"transformation":[9,46,77,110],"of":[10,14,51,66,85,101,111,125,128,130],"the":[11,31,38,79,83,86,96,126,131],"characteristic":[12,22],"features":[13,23,33,53,58],"source":[16],"speaker":[17],"towards":[18],"target.":[20],"Voice":[21],"are":[24,54,61],"grouped":[25],"into":[26],"two":[27],"main":[28],"categories:":[29],"(a)":[30],"spectral":[32,57],"at":[34,59],"formants":[35,60],"and":[36,40,45,98,115,122],"(b)":[37],"pitch":[39,97],"intonation":[41,99,113],"patterns.":[42],"Signal":[43],"modelling":[44,95],"methods":[47],"for":[48,75,94,109],"each":[49],"group":[50],"outlined.":[55],"The":[56,89,118],"modelled":[62],"using":[63],"set":[65],"two-dimensional":[67],"phoneme-dependent":[68],"HMM.":[69],"Subband":[70],"frequency":[71],"warping":[72],"is":[73,92,107],"used":[74,93],"spectrum":[76],"with":[78],"subbands":[80],"centred":[81],"estimates":[84],"formant":[87],"trajectories.":[88],"F0":[90],"contour":[91],"patterns":[100,114],"speech.":[102],"A":[103],"PSOLA":[104],"employed":[108],"pitch,":[112],"speaking":[116],"rate.":[117],"experiments":[119],"present":[120],"illustrations":[121],"perceptual":[123],"evaluations":[124],"results":[127],"transformations":[129],"various":[132],"features.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
