{"id":"https://openalex.org/W2782893980","doi":"https://doi.org/10.1109/iske.2017.8258822","title":"High quality voice conversion based on ISODATA clustering algorithm","display_name":"High quality voice conversion based on ISODATA clustering algorithm","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2782893980","doi":"https://doi.org/10.1109/iske.2017.8258822","mag":"2782893980"},"language":"en","primary_location":{"id":"doi:10.1109/iske.2017.8258822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iske.2017.8258822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","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/A5100385632","display_name":"Yanping Li","orcid":"https://orcid.org/0000-0002-0074-7695"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanping Li","raw_affiliation_strings":["College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056292751","display_name":"Yutao Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Zuo","raw_affiliation_strings":["College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047980942","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-4400-3823"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040075114","display_name":"Xi Shao","orcid":"https://orcid.org/0000-0002-2348-7515"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Shao","raw_affiliation_strings":["College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100385632"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19195429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962000250816345,"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":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.756686806678772},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7555383443832397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6739414930343628},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5918253064155579},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5879518985748291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5564485192298889},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5229732990264893},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43099260330200195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4051669239997864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3592115640640259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756686806678772},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7555383443832397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6739414930343628},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5918253064155579},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5879518985748291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5564485192298889},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5229732990264893},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43099260330200195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4051669239997864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3592115640640259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iske.2017.8258822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iske.2017.8258822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W257263969","https://openalex.org/W2121387787","https://openalex.org/W2156142001","https://openalex.org/W2164028031","https://openalex.org/W2165674530","https://openalex.org/W2179428711","https://openalex.org/W2473388484","https://openalex.org/W2576309025","https://openalex.org/W2651834199","https://openalex.org/W2747210965","https://openalex.org/W2747753032","https://openalex.org/W3124274650","https://openalex.org/W4231951313","https://openalex.org/W6609663617"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2181956362","https://openalex.org/W2136153680","https://openalex.org/W2972577568","https://openalex.org/W2148323604"],"abstract_inverted_index":{"Two":[0],"main":[1],"challenges":[2],"introduced":[3],"in":[4],"current":[5],"voice":[6],"conversion":[7,34,100],"are":[8],"the":[9,16,26,52,58,64,69,99,121],"dependence":[10],"on":[11,37],"parallel":[12],"training":[13,53],"data":[14],"and":[15,21,66,86,94,111,116,128],"trade-off":[17],"between":[18,82,108],"speaker":[19,80,109],"similarity":[20,81,110,129],"speech":[22,85,112],"quality.":[23,113],"To":[24],"tackle":[25],"latter":[27],"problem,":[28],"this":[29],"paper":[30],"proposes":[31],"a":[32,105],"novel":[33],"method":[35],"based":[36],"Iterative":[38],"Self-organizing":[39],"DATA":[40],"Analysis":[41],"Techniques":[42],"Algorithm":[43],"(ISODATA)":[44],"clustering":[45],"algorithm.":[46],"Specially,":[47],"we":[48,90],"use":[49],"ISODATA":[50],"during":[51],"of":[54,68],"Gaussian":[55],"mixture":[56,60],"model,":[57,71],"optimized":[59],"number":[61],"can":[62,73,103,124],"guarantee":[63],"validity":[65],"accuracy":[67],"GMM":[70,93],"which":[72,102],"acquire":[74],"speaker's":[75],"identity":[76],"effectively":[77],"related":[78],"to":[79],"original":[83],"target":[84],"converted":[87],"speech,":[88],"Next,":[89],"combine":[91],"improved":[92],"bilinear":[95],"frequency":[96],"warping":[97],"for":[98],"stage,":[101],"get":[104],"good":[106],"balance":[107],"Theory":[114],"analysis":[115],"experimental":[117],"results":[118],"demonstrate":[119],"that":[120],"proposed":[122],"algorithm":[123],"achieve":[125],"higher":[126],"quality":[127],"compared":[130],"with":[131],"other":[132],"two":[133],"methods.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}