{"id":"https://openalex.org/W2532202862","doi":"https://doi.org/10.1109/iscslp.2016.7918382","title":"Dictionary update for NMF-based voice conversion using an encoder-decoder network","display_name":"Dictionary update for NMF-based voice conversion using an encoder-decoder network","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2532202862","doi":"https://doi.org/10.1109/iscslp.2016.7918382","mag":"2532202862"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th 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/A5028115568","display_name":"Chin-Cheng Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chin-Cheng Hsu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101061014","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028115568"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":1.2852,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87203811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"22","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":0.9998000264167786,"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":0.9976999759674072,"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":0.9825000166893005,"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":0.8679283261299133},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8594074249267578},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6990698575973511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400333642959595},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.504004180431366},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.49977660179138184},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4982333183288574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4471997618675232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44031578302383423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42586636543273926},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42090919613838196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3612881898880005},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09122714400291443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8679283261299133},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8594074249267578},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6990698575973511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400333642959595},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.504004180431366},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.49977660179138184},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4982333183288574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4471997618675232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44031578302383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42586636543273926},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42090919613838196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3612881898880005},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09122714400291443},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1517202054","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1977362459","https://openalex.org/W2017425464","https://openalex.org/W2049686551","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2135029798","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2157412983","https://openalex.org/W2290463584","https://openalex.org/W2294351487","https://openalex.org/W2405032154","https://openalex.org/W2473388484","https://openalex.org/W2512087624","https://openalex.org/W2577042574","https://openalex.org/W2964121744","https://openalex.org/W3143596294","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6680012447","https://openalex.org/W6696767757","https://openalex.org/W6732251480"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2900450731"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,116],"propose":[4,117],"a":[5,19,63,75,90,118],"dictionary":[6,94,102,119],"update":[7,120],"method":[8],"for":[9,58,122],"Non-negative":[10],"Matrix":[11],"Factorization":[12],"(NMF)":[13],"with":[14,162,169],"high":[15],"dimensional":[16],"data":[17],"in":[18,104],"spectral":[20],"conversion":[21,25],"(SC)":[22],"task.":[23],"Voice":[24],"has":[26],"been":[27],"widely":[28],"studied":[29],"due":[30],"to":[31,81,99,139,151],"its":[32],"potential":[33],"applications":[34],"such":[35,109],"as":[36,47,60,62,110,132],"personalized":[37],"speech":[38,41,66],"synthesis":[39],"and":[40,50,92,147],"enhancement.":[42],"Exemplar-based":[43],"NMF":[44,123,131],"(ENMF)":[45],"emerges":[46],"an":[48,127,133],"effective":[49,93],"probably":[51],"the":[52,83,86,141,159],"simplest":[53],"choice":[54],"among":[55],"all":[56],"techniques":[57],"SC,":[59],"long":[61],"source-target":[64],"parallel":[65,143],"corpus":[67,144],"is":[68,95],"given.":[69],"ENMF-based":[70,167],"SC":[71],"systems":[72,168],"usually":[73],"need":[74],"large":[76],"amount":[77],"of":[78,85,126,158,171],"bases":[79],"(exemplars)":[80],"ensure":[82],"quality":[84],"converted":[87],"speech.":[88],"However,":[89],"small":[91,163],"desirable":[96],"but":[97],"hard":[98],"obtain":[100],"via":[101],"update,":[103],"particular":[105],"when":[106,149],"high-dimensional":[107],"features":[108],"STRAIGHT":[111],"spectra":[112],"are":[113],"used.":[114],"Therefore,":[115],"framework":[121],"by":[124],"means":[125],"encoder-decoder":[128,134],"reformulation.":[129],"Regarding":[130],"network":[135],"makes":[136],"it":[137],"possible":[138],"exploit":[140],"whole":[142],"more":[145],"effectively":[146],"efficiently":[148],"applied":[150],"SC.":[152],"Our":[153],"experiments":[154],"demonstrate":[155],"significant":[156],"gains":[157],"proposed":[160],"system":[161],"dictionaries":[164,170],"over":[165],"conventional":[166],"same":[172],"or":[173],"much":[174],"larger":[175],"size.":[176]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}