{"id":"https://openalex.org/W2963658876","doi":"https://doi.org/10.21437/interspeech.2018-1506","title":"Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions","display_name":"Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963658876","doi":"https://doi.org/10.21437/interspeech.2018-1506","mag":"2963658876"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5100749025","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0003-3634-2275"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Gu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047212809","display_name":"Yongguo Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongguo Kang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100749025"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7917,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89045863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2007","last_page":"2011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9929999709129333,"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":0.9765999913215637,"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/speech-synthesis","display_name":"Speech synthesis","score":0.7804721593856812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523709535598755},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6665353775024414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6580827832221985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6262047290802002},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6190802454948425},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5668783187866211},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.519821286201477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5129992365837097},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46459007263183594},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4575769603252411},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44211870431900024},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4141473174095154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33528411388397217},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12279075384140015},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1172899603843689},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09493416547775269}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7804721593856812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523709535598755},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6665353775024414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6580827832221985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6262047290802002},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6190802454948425},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5668783187866211},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.519821286201477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5129992365837097},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46459007263183594},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4575769603252411},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44211870431900024},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4141473174095154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33528411388397217},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12279075384140015},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1172899603843689},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09493416547775269},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2039489009","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"This":[0],"paper":[1,106],"introduces":[2],"an":[3],"improved":[4,57],"generative":[5],"model":[6,47],"for":[7,48],"statistical":[8],"parametric":[9],"speech":[10,62,77],"synthesis":[11],"(SPSS)":[12],"based":[13],"on":[14,66],"WaveNet":[15,25,30,51,58,70,118],"under":[16],"a":[17],"multi-task":[18],"learning":[19],"framework.":[20],"Different":[21],"from":[22],"the":[23,27,32,38,42,49,56,80,93,100,112,116],"original":[24,50,94,117],"model,":[26],"proposed":[28,103],"Multi-task":[29,69],"employs":[31],"frame-level":[33],"acoustic":[34],"feature":[35],"prediction":[36,46,82],"as":[37],"secondary":[39],"task":[40],"and":[41,75,86,122],"external":[43],"fundamental":[44],"frequency":[45],"can":[52,59,71,107],"be":[53],"removed.":[54],"Therefore":[55],"generate":[60],"high-quality":[61],"waveforms":[63],"only":[64],"conditioned":[65],"linguistic":[67],"features.":[68],"produce":[72],"more":[73,88],"natural":[74],"expressive":[76],"by":[78],"addressing":[79],"pitch":[81],"error":[83],"accumulation":[84],"issue":[85],"possesses":[87],"succinct":[89],"inference":[90],"procedures":[91],"than":[92,111],"WaveNet.":[95],"Experimental":[96],"results":[97],"prove":[98],"that":[99],"SPSS":[101],"method":[102],"in":[104,119],"this":[105],"achieve":[108],"better":[109],"performance":[110],"state-of-the-art":[113],"approach":[114],"utilizing":[115],"both":[120],"objective":[121],"subjective":[123],"preference":[124],"tests.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}