{"id":"https://openalex.org/W2133868607","doi":"https://doi.org/10.1109/icassp.2009.4960575","title":"Phoneme cluster based state mapping for text-independent voice conversion","display_name":"Phoneme cluster based state mapping for text-independent voice conversion","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2133868607","doi":"https://doi.org/10.1109/icassp.2009.4960575","mag":"2133868607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5100437809","display_name":"Meng Zhang","orcid":"https://orcid.org/0000-0003-2188-8195"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Zhang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026684336","display_name":"Jiaohua Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaohua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112039585","display_name":"Jani Nurminen","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jani Nurminen","raw_affiliation_strings":["Nokia Devices Research And Development, Tampere, Finland","Nokia Devices R&D, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Devices Research And Development, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Devices R&D, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":["Nokia Research Center, Tampere, Finland","Nokia Res. Center, Tampere, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Res. Center, Tampere, Finland#TAB#","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397888","display_name":"Xia Wang","orcid":"https://orcid.org/0000-0001-5655-2291"},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]},{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Xia Wang","raw_affiliation_strings":["Nokia Research Center, Tampere, Finland","Nokia Research Center Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Research Center Beijing, China","institution_ids":["https://openalex.org/I4210099903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100437809"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":1.3085,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84890512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4281","last_page":"4284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T12031","display_name":"Speech and dialogue systems","score":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8337030410766602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7881269454956055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7295745611190796},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6636295318603516},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5448141694068909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146545171737671},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5081503391265869},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41775667667388916},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41388797760009766},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4120989441871643},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3548921048641205},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13744789361953735},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06451016664505005}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8337030410766602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881269454956055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7295745611190796},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6636295318603516},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5448141694068909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146545171737671},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5081503391265869},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41775667667388916},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41388797760009766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4120989441871643},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3548921048641205},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13744789361953735},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06451016664505005},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W33829787","https://openalex.org/W152891837","https://openalex.org/W2033641795","https://openalex.org/W2049686551","https://openalex.org/W2111550316","https://openalex.org/W2152974894","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2169579015","https://openalex.org/W6601306257"],"related_works":["https://openalex.org/W879529032","https://openalex.org/W2038801705","https://openalex.org/W155946340","https://openalex.org/W2110108310","https://openalex.org/W1846837356","https://openalex.org/W2108224380","https://openalex.org/W2216757598","https://openalex.org/W1845608487","https://openalex.org/W2133868607","https://openalex.org/W2147462851"],"abstract_inverted_index":{"This":[0],"paper":[1],"takes":[2],"phonetic":[3,22,93],"information":[4,49,94],"into":[5],"account":[6],"for":[7,19],"data":[8],"alignment":[9],"in":[10,76],"text-independent":[11],"voice":[12,114],"conversion.":[13,115],"Hidden":[14],"Markov":[15],"models":[16],"are":[17,32,71],"used":[18],"representing":[20],"the":[21,51,89,96],"structure":[23],"of":[24,92],"training":[25],"speech.":[26,103],"States":[27],"belonging":[28],"to":[29,35,78,109],"same":[30],"phoneme":[31,38,53],"grouped":[33],"together":[34],"form":[36],"a":[37,80],"cluster.":[39],"A":[40],"state":[41],"mapped":[42],"codebook":[43],"based":[44],"transformation":[45],"is":[46,107],"established":[47],"using":[48],"on":[50],"corresponding":[52],"clusters":[54,70],"from":[55],"source":[56,66],"and":[57,60,82,101,112],"targets":[58],"speech":[59,100],"weighted":[61],"linear":[62],"transform.":[63,84],"For":[64],"each":[65],"vector,":[67],"several":[68],"nearest":[69],"considered":[72],"simultaneously":[73],"while":[74],"mapping":[75],"order":[77],"generate":[79],"continuous":[81],"stable":[83],"Experimental":[85],"results":[86],"indicate":[87],"that":[88],"proposed":[90,105],"use":[91],"increases":[95],"similarity":[97],"between":[98],"converted":[99],"target":[102],"The":[104],"technique":[106],"applicable":[108],"both":[110],"intra-lingual":[111],"cross-lingual":[113]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
