{"id":"https://openalex.org/W1973685422","doi":"https://doi.org/10.1109/iscslp.2010.5684869","title":"GMM-based voice conversion with explicit modelling on feature transform","display_name":"GMM-based voice conversion with explicit modelling on feature transform","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1973685422","doi":"https://doi.org/10.1109/iscslp.2010.5684869","mag":"1973685422"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language 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/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"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":"Ling-Hui Chen","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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":"Zhen-Hua Ling","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101085190","display_name":"Wu Guo","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":"Wu Guo","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"Li-Rong Dai","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101593418"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.80163843,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78384264,"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":"364","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9904999732971191,"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/mixture-model","display_name":"Mixture model","score":0.8221474885940552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6060426831245422},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.576852560043335},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5616381764411926},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.557784378528595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5095498561859131},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4862012267112732},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4807126820087433},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.4562133848667145},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4522252678871155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43014898896217346},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4213297665119171},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3931431472301483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3651995062828064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33669984340667725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33660441637039185},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11808046698570251}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8221474885940552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060426831245422},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.576852560043335},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5616381764411926},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.557784378528595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5095498561859131},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4862012267112732},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4807126820087433},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.4562133848667145},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4522252678871155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43014898896217346},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4213297665119171},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3931431472301483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3651995062828064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33669984340667725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33660441637039185},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11808046698570251},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1973532181","https://openalex.org/W2049686551","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2145130307","https://openalex.org/W2154920538","https://openalex.org/W2156142001"],"related_works":["https://openalex.org/W2075383893","https://openalex.org/W4300066510","https://openalex.org/W1971337326","https://openalex.org/W2056958800","https://openalex.org/W4213259725","https://openalex.org/W4311388919","https://openalex.org/W1964490787","https://openalex.org/W2060696366","https://openalex.org/W2154788797","https://openalex.org/W1992295166"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"Gaussian":[6],"mixture":[7],"model":[8,81],"(GMM)":[9],"based":[10],"voice":[11,116],"conversion":[12],"method":[13,79,108,113],"using":[14],"explicit":[15,42],"feature":[16],"transform":[17,22],"models.":[18],"A":[19],"piecewise":[20],"linear":[21],"with":[23,67,97,99],"stochastic":[24],"bias":[25],"is":[26,70],"adopted":[27],"to":[28,72],"present":[29],"the":[30,33,47,52,74,82,86,106,110],"relationship":[31],"between":[32],"spectral":[34,76],"features":[35,69],"of":[36,49,56],"source":[37,57],"and":[38,58],"target":[39,59],"speakers.":[40],"This":[41],"transformations":[43],"are":[44],"integrated":[45],"into":[46],"training":[48],"GMM":[50,89],"for":[51,85],"joint":[53,87],"probability":[54],"density":[55,88],"features.":[60],"The":[61],"maximum":[62],"likelihood":[63],"parameter":[64],"generation":[65],"algorithm":[66],"dynamic":[68],"used":[71],"generate":[73],"converted":[75],"trajectories.":[77],"Our":[78],"can":[80],"cross-dimension":[83],"correlations":[84],"(JDGMM),":[90],"while":[91],"significantly":[92],"decreasing":[93],"computation":[94],"cost":[95],"comparing":[96],"JDGMM":[98],"full":[100],"covariance.":[101],"Experimental":[102],"results":[103],"show":[104],"that":[105],"proposed":[107],"outperformed":[109],"conventional":[111],"GMM-based":[112],"in":[114],"cross-gender":[115],"conversion.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"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"}