{"id":"https://openalex.org/W2398319638","doi":"https://doi.org/10.21437/interspeech.2004-445","title":"A novel voice conversion system based on codebook mapping with phoneme-tied weighting","display_name":"A novel voice conversion system based on codebook mapping with phoneme-tied weighting","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W2398319638","doi":"https://doi.org/10.21437/interspeech.2004-445","mag":"2398319638"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5086141660","display_name":"Zixiang Wang","orcid":"https://orcid.org/0000-0002-9956-621X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixiang Wang","raw_affiliation_strings":["Univ. of Sci. and Tech. of China"],"affiliations":[{"raw_affiliation_string":"Univ. of Sci. and Tech. of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102734836","display_name":"Ren-Hua Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renhua Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071906610","display_name":"Zhiwei Shuang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Shuang","raw_affiliation_strings":["Univ. of Sci. and Tech. of China"],"affiliations":[{"raw_affiliation_string":"Univ. of Sci. and Tech. of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086141660"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.6982,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91337189,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1197","last_page":"1200"},"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":0.9993000030517578,"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":0.9927999973297119,"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/codebook","display_name":"Codebook","score":0.9554724097251892},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7691569328308105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7436367869377136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6799742579460144},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5533096790313721},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5317688584327698},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4797171950340271},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4562247395515442},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42177462577819824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3919965326786041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0818549394607544}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9554724097251892},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7691569328308105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436367869377136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6799742579460144},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5533096790313721},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5317688584327698},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4797171950340271},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4562247395515442},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42177462577819824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3919965326786041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0818549394607544},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W138059918","https://openalex.org/W2049686551","https://openalex.org/W2067234399","https://openalex.org/W2118850452"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W2136885550","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,31,78],"novel":[4],"voice":[5],"conversion":[6,34],"system":[7],"based":[8],"on":[9],"codebook":[10],"mapping.":[11],"A":[12],"new":[13,32],"phoneme-tied":[14],"weighting":[15],"strategy":[16],"is":[17,39,51],"proposed":[18,40,65],"to":[19,41,53],"reduce":[20],"the":[21,44,64],"smoothing":[22],"effects":[23],"in":[24],"weighted":[25],"sum":[26],"of":[27,47,81],"code":[28],"books,":[29],"while":[30,72],"prosodic":[33],"method":[35],"by":[36],"decision":[37],"tree":[38],"cope":[42],"with":[43,77],"complex":[45],"prosody":[46],"Chinese.":[48],"STRAIGHT":[49],"algorithm":[50],"used":[52],"decompose":[54],"spectrum":[55],"and":[56],"excitation":[57],"for":[58],"separate":[59],"modification.":[60],"Listening":[61],"tests":[62],"prove":[63],"methods":[66],"can":[67],"effectively":[68],"convert":[69],"speaker\u2019s":[70],"individuality":[71],"maintaining":[73],"high":[74],"speech":[75],"quality":[76],"small":[79],"amount":[80],"training":[82],"data.":[83]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
