{"id":"https://openalex.org/W2963175743","doi":"https://doi.org/10.1109/icassp.2019.8682298","title":"Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis","display_name":"Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963175743","doi":"https://doi.org/10.1109/icassp.2019.8682298","mag":"2963175743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":130,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5916","last_page":"5920"},"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":0.9990000128746033,"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":0.9918000102043152,"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/waveform","display_name":"Waveform","score":0.8791267275810242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7349273562431335},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.599422812461853},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5892331004142761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5680484771728516},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5438166260719299},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5313067436218262},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5006167888641357},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47675761580467224},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.459448903799057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34999775886535645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11832520365715027},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09011730551719666}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8791267275810242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349273562431335},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.599422812461853},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5892331004142761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5680484771728516},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5438166260719299},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5313067436218262},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5006167888641357},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47675761580467224},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.459448903799057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34999775886535645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11832520365715027},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09011730551719666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":30,"referenced_works":["https://openalex.org/W169745891","https://openalex.org/W304834817","https://openalex.org/W1496971974","https://openalex.org/W1594680456","https://openalex.org/W1976313025","https://openalex.org/W2003513484","https://openalex.org/W2135029798","https://openalex.org/W2144499799","https://openalex.org/W2164764235","https://openalex.org/W2194775991","https://openalex.org/W2394921947","https://openalex.org/W2405614646","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2587284713","https://openalex.org/W2749651610","https://openalex.org/W2749881488","https://openalex.org/W2769810959","https://openalex.org/W2886022419","https://openalex.org/W2949382160","https://openalex.org/W2963522141","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964041258","https://openalex.org/W2964243274","https://openalex.org/W4294619240","https://openalex.org/W6680012447","https://openalex.org/W6712208827","https://openalex.org/W6733471323","https://openalex.org/W6753855596"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W4367555392","https://openalex.org/W2374664672","https://openalex.org/W2056136368","https://openalex.org/W2538520412","https://openalex.org/W2039489009"],"abstract_inverted_index":{"Neural":[0],"waveform":[1,22,66],"models":[2,33],"such":[3],"as":[4],"the":[5,15,44,52,78,84,88,110,114,122,133,137,151,160,165,172,175],"WaveNet":[6,17,135],"are":[7],"used":[8],"in":[9,21],"many":[10],"recent":[11],"text-to-speech":[12],"systems,":[13],"but":[14],"original":[16],"is":[18,143],"quite":[19],"slow":[20],"generation":[23],"because":[24],"of":[25,46,54,139,147,174],"its":[26,140],"autoregressive":[27],"(AR)":[28],"structure.":[29],"Although":[30],"faster":[31,131],"non-AR":[32,63],"were":[34,169],"recently":[35],"reported,":[36],"they":[37],"may":[38],"be":[39,70],"prohibitively":[40],"complicated":[41],"due":[42],"to":[43,96,108,145,171],"use":[45],"a":[47,62,93,98,105],"distilling":[48],"training":[49,57,75,167],"method":[50],"and":[51,77,102,136,164],"blend":[53],"other":[55],"disparate":[56],"criteria.":[58],"This":[59],"study":[60],"proposes":[61],"neural":[64],"source-filter":[65],"model":[67,90,124],"that":[68,121,146,158],"can":[69],"directly":[71],"trained":[72],"using":[73],"spectrum-based":[74,166],"criteria":[76,168],"stochastic":[79],"gradient":[80],"descent":[81],"method.":[82],"Given":[83],"input":[85],"acoustic":[86],"features,":[87],"proposed":[89,123,176],"first":[91],"uses":[92,104],"source":[94],"module":[95,107],"generate":[97],"sine-based":[99],"excitation":[100,111,162],"signal":[101,112,163],"then":[103],"filter":[106],"transform":[109],"into":[113],"output":[115],"speech":[116,142,148],"waveform.":[117],"Our":[118],"experiments":[119],"demonstrated":[120],"generated":[125,149],"waveforms":[126],"at":[127],"least":[128],"100":[129],"times":[130],"than":[132],"AR":[134,152],"quality":[138],"synthetic":[141],"close":[144],"by":[150],"WaveNet.":[153],"Ablation":[154],"test":[155],"results":[156],"showed":[157],"both":[159],"sine-wave":[161],"essential":[170],"performance":[173],"model.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}