{"id":"https://openalex.org/W2944173394","doi":"https://doi.org/10.1109/iscslp.2018.8706660","title":"Frame Selection in SI-DNN Phonetic Space with WaveNet Vocoder for Voice Conversion without Parallel Training Data","display_name":"Frame Selection in SI-DNN Phonetic Space with WaveNet Vocoder for Voice Conversion without Parallel Training Data","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944173394","doi":"https://doi.org/10.1109/iscslp.2018.8706660","mag":"2944173394"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng-Long Xie","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442261","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-5218-2761"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Microsoft Cloud and AI, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud and AI, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft Cloud and AI, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud and AI, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103652315","display_name":"Li Haifeng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Haifeng","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101692260"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21385831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"56","last_page":"60"},"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":0.9979000091552734,"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":0.991100013256073,"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":0.7594742774963379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7015487551689148},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4499283730983734},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4455976188182831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37018316984176636},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07191428542137146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594742774963379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7015487551689148},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4499283730983734},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4455976188182831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37018316984176636},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07191428542137146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1519698338","https://openalex.org/W1520370180","https://openalex.org/W1965555277","https://openalex.org/W1977362459","https://openalex.org/W2024490156","https://openalex.org/W2032130465","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2135832479","https://openalex.org/W2152974894","https://openalex.org/W2154920538","https://openalex.org/W2157412983","https://openalex.org/W2161476805","https://openalex.org/W2294246205","https://openalex.org/W2398071208","https://openalex.org/W2401544731","https://openalex.org/W2404839462","https://openalex.org/W2514429423","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2746474733","https://openalex.org/W2747161606","https://openalex.org/W2749651610","https://openalex.org/W2785608393","https://openalex.org/W2797310469","https://openalex.org/W2890402938","https://openalex.org/W2962896155","https://openalex.org/W2963808252","https://openalex.org/W2964243274","https://openalex.org/W3177989406","https://openalex.org/W6630475647","https://openalex.org/W6656414902","https://openalex.org/W6697270646","https://openalex.org/W6713064456","https://openalex.org/W7009720900"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,93],"propose":[4],"a":[5],"frame":[6,54],"selection":[7,109],"approach":[8],"to":[9,49,83],"voice":[10],"conversion":[11],"with":[12,33,67,127,139,160],"speaker":[13,30,120,155],"independent":[14],"deep":[15],"neural":[16],"network":[17],"(SIDNN)":[18],"and":[19,28,119,166,170],"Kullback-Leibler":[20],"divergence":[21],"(KLD).":[22],"The":[23],"acoustic":[24,81],"difference":[25],"between":[26],"source":[27,57],"target":[29,53,154],"is":[31,42,65,76],"equalized":[32],"SI-DNN":[34],"in":[35],"the":[36,51,56,62,79,85,90,97,105,117,150],"ASR":[37],"senone":[38],"phonetic":[39,106],"space.":[40],"KLD":[41],"used":[43],"as":[44],"an":[45],"ideal":[46],"distortion":[47],"measure":[48],"select":[50],"corresponding":[52],"given":[55],"frame.":[58],"Acoustic":[59],"trajectory":[60,70,82],"of":[61],"selected":[63],"frames":[64],"rendered":[66],"maximum":[68],"probability":[69],"generation":[71],"algorithm.":[72],"WaveNet":[73,115,135,157],"based":[74,108,132],"vocoder":[75,116,136,158],"applied":[77],"on":[78],"converted":[80],"get":[84],"final":[86],"speech":[87],"waveform.":[88],"From":[89],"subjective":[91],"results":[92],"find":[94],"that":[95],"1)":[96],"proposed":[98],"method":[99,110],"can":[100,122,147],"achieve":[101],"better":[102,148],"performance":[103],"than":[104,156],"cluster":[107],"[16];":[111],"2)":[112],"by":[113],"applying":[114],"naturalness":[118],"similarity":[121],"be":[123],"significantly":[124],"improved":[125],"compared":[126],"linear":[128],"predictive":[129],"coding":[130],"(LPC)":[131],"vocoder;":[133],"3)":[134],"trained":[137,159],"only":[138],"spectral":[140,162],"features":[141,163,168],"i.e.,":[142,164],"line":[143],"spectrum":[144],"pairs":[145],"(LSP)":[146],"maintain":[149],"pitch":[151],"pattern":[152],"towards":[153],"both":[161],"LSP":[165],"prosodic":[167],"(F0":[169],"Unvoiced/Voiced":[171],"flag).":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}