{"id":"https://openalex.org/W2128685417","doi":"https://doi.org/10.1109/icassp.2011.5947508","title":"Non-parallel training for voice conversion based on FT-GMM","display_name":"Non-parallel training for voice conversion based on FT-GMM","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2128685417","doi":"https://doi.org/10.1109/icassp.2011.5947508","mag":"2128685417"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5396,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64309617,"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":"5116","last_page":"5119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9983999729156494,"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":0.9843999743461609,"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":0.8800352811813354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7128835916519165},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6495543122291565},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6154483556747437},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5868303775787354},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.560531735420227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4846954643726349},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.44709745049476624},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.44544780254364014},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4363557994365692},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4363557994365692},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43022263050079346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41444146633148193},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3694990277290344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06472617387771606}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8800352811813354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128835916519165},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6495543122291565},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6154483556747437},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5868303775787354},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.560531735420227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4846954643726349},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.44709745049476624},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.44544780254364014},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4363557994365692},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4363557994365692},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43022263050079346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41444146633148193},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3694990277290344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06472617387771606},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.7200000286102295,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W59075858","https://openalex.org/W1973685422","https://openalex.org/W2002342963","https://openalex.org/W2049686551","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2145130307","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2169878657","https://openalex.org/W3177989406","https://openalex.org/W6602386084","https://openalex.org/W6798679566"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048"],"abstract_inverted_index":{"This":[0,68],"paper":[1],"presents":[2],"a":[3,22],"non-parallel":[4,77],"training":[5,78],"algorithm":[6],"for":[7,87],"voice":[8],"con":[9],"version":[10],"based":[11],"on":[12],"feature":[13,37,66],"transform":[14,38],"Gaussian":[15],"mixture":[16,23,55],"model":[17,24,56,75],"(FT":[18],"GMM),":[19],"which":[20],"is":[21,98],"of":[25,29,47,53],"joint":[26],"density":[27],"space":[28],"source":[30,110],"speaker":[31,34,89],"and":[32,90,111],"target":[33,112],"with":[35],"explicit":[36,65],"modeling.":[39],"In":[40],"FT-GMM,":[41],"the":[42,45,54,119],"correlations":[43],"between":[44,109],"distributions":[46],"two":[48,84],"speakers":[49],"in":[50],"each":[51,88],"component":[52],"are":[57],"not":[58],"directly":[59],"modeled,":[60],"but":[61],"absorbed":[62],"into":[63,83],"these":[64],"transformations.":[67],"makes":[69],"it":[70,82],"possible":[71],"to":[72,76,100],"extend":[73],"this":[74],"by":[79,105],"simply":[80],"decomposing":[81],"sub-models,":[85],"one":[86],"optimizing":[91],"them":[92],"separatively.":[93],"A":[94],"frequency":[95],"warping":[96],"process":[97],"adopted":[99],"compensate":[101],"performance":[102,124],"degradation":[103],"caused":[104],"original":[106],"spectral":[107],"distance":[108],"speakers.":[113],"Cross-gender":[114],"experimental":[115],"results":[116],"show":[117],"that":[118],"proposed":[120],"method":[121],"achieves":[122],"comparable":[123],"as":[125],"parallel":[126],"training.":[127]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}