{"id":"https://openalex.org/W2911340057","doi":"https://doi.org/10.1109/slt.2018.8639507","title":"Adaptive Wavenet Vocoder for Residual Compensation in GAN-Based Voice Conversion","display_name":"Adaptive Wavenet Vocoder for Residual Compensation in GAN-Based Voice Conversion","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2911340057","doi":"https://doi.org/10.1109/slt.2018.8639507","mag":"2911340057"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432821","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0002-9768-516X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001303929"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":6.5153,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.9730553,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"282","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9965999722480774,"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/naturalness","display_name":"Naturalness","score":0.7887169122695923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557002305984497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7070824503898621},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6165108680725098},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6148837208747864},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5644227862358093},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5577918887138367},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4481481909751892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3418843746185303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12572547793388367}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7887169122695923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557002305984497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7070824503898621},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6165108680725098},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6148837208747864},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5644227862358093},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5577918887138367},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4481481909751892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418843746185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12572547793388367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/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/slt.2018.8639507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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":56,"referenced_works":["https://openalex.org/W79241043","https://openalex.org/W1509691205","https://openalex.org/W1517202054","https://openalex.org/W1965912016","https://openalex.org/W1977362459","https://openalex.org/W2005438552","https://openalex.org/W2017425464","https://openalex.org/W2086796102","https://openalex.org/W2105160541","https://openalex.org/W2107860279","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2151262064","https://openalex.org/W2269051851","https://openalex.org/W2293049663","https://openalex.org/W2396025094","https://openalex.org/W2402356521","https://openalex.org/W2407039802","https://openalex.org/W2484196375","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2605762339","https://openalex.org/W2608338293","https://openalex.org/W2666408839","https://openalex.org/W2746457594","https://openalex.org/W2746474733","https://openalex.org/W2747744257","https://openalex.org/W2749371885","https://openalex.org/W2749651610","https://openalex.org/W2758785877","https://openalex.org/W2774848319","https://openalex.org/W2785608393","https://openalex.org/W2785978752","https://openalex.org/W2786868129","https://openalex.org/W2889064624","https://openalex.org/W2907162034","https://openalex.org/W2949382160","https://openalex.org/W2962850167","https://openalex.org/W2962896155","https://openalex.org/W2963341071","https://openalex.org/W2963539064","https://openalex.org/W2963618559","https://openalex.org/W2963971656","https://openalex.org/W2964024144","https://openalex.org/W2964243274","https://openalex.org/W3142619648","https://openalex.org/W6711854987","https://openalex.org/W6714093102","https://openalex.org/W6722217012","https://openalex.org/W6736494419","https://openalex.org/W6737196085","https://openalex.org/W6744040789","https://openalex.org/W6745117592","https://openalex.org/W6746801104","https://openalex.org/W6748381320"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W3100825170","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2946856121","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W3149582125"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,96],"propose":[4],"to":[5,16,27,31,43,72,99,106],"use":[6,100],"generative":[7],"adversarial":[8],"networks":[9],"(GAN)":[10],"together":[11],"with":[12],"a":[13,79],"WaveNet":[14,68,101],"vocoder":[15,69,102],"address":[17],"the":[18,23,33,37,45,48,57,61,65,75,85,88,93,108,116,123],"over-smoothing":[19,58],"problem":[20,59],"arising":[21],"from":[22,74],"deep":[24],"learning":[25],"approaches":[26],"voice":[28,109,118],"conversion,":[29],"and":[30,50],"improve":[32,107],"vocoding":[34],"quality":[35],"over":[36],"traditional":[38],"vocoders.":[39],"As":[40],"GAN":[41],"aims":[42],"minimize":[44],"divergence":[46],"between":[47],"natural":[49],"converted":[51,62],"speech":[52,77],"parameters,":[53],"it":[54],"effectively":[55],"alleviates":[56],"in":[60],"speech.":[63],"On":[64],"other":[66],"hand,":[67],"allows":[70],"us":[71],"leverage":[73],"human":[76],"of":[78,87],"large":[80],"speaker":[81],"population,":[82],"thus":[83],"improving":[84],"naturalness":[86],"synthetic":[89],"voice.":[90],"Furthermore,":[91],"for":[92,103],"first":[94],"time,":[95],"study":[97],"how":[98],"residual":[104],"compensation":[105],"conversion":[110,119],"performance.":[111],"The":[112],"experiments":[113],"show":[114],"that":[115],"proposed":[117],"framework":[120],"consistently":[121],"outperforms":[122],"baselines.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}