{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:28Z","timestamp":1740172468471,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0140002"],"award-info":[{"award-number":["2020AAA0140002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101553","61831022","61901473","61771472"],"award-info":[{"award-number":["62101553","61831022","61901473","61771472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Inria-CAS Joint Research Project","award":["173211KYSB 20190049"],"award-info":[{"award-number":["173211KYSB 20190049"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3140480","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T20:38:29Z","timestamp":1641415109000},"page":"865-878","source":"Crossref","is-referenced-by-count":0,"title":["NeuralDPS: Neural Deterministic Plus Stochastic Model With Multiband Excitation for Noise-Controllable Waveform Generation"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1490-6973","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-1881","authenticated-orcid":false,"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0048-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1979.1094454"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.326413"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-50204-5","volume-title":"Speech Coding: With Code-Excited Linear Prediction","author":"Bckstrm","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-541"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref13","article-title":"An experimental comparison of multiple vocoder types","volume-title":"Proc. 8th ISCA Workshop Speech Synth.","author":"Hu","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172444"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2307\/3680093"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/89.890068"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2169787"},{"issue":"7553","key":"ref19","first-page":"436","article-title":"Deep learning","volume-title":"Nature","volume":"521","author":"LeCun","year":"2015"},{"key":"ref20","article-title":"WaveNet: A generative model for raw audio","volume-title":"SSW","volume":"125","author":"Van Den Oord","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"An introduction to convolutional neural networks","year":"2015","author":"OShea","key":"ref22"},{"key":"ref23","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","year":"2016","author":"Mehri","key":"ref24"},{"key":"ref25","first-page":"3918","article-title":"Parallel waveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref28","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Adv. Neural Inf. process. syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref29","first-page":"17033","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref30","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng","year":"2020"},{"article-title":"Diffwave: A versatile diffusion model for audio synthesis","year":"2020","author":"Kong","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2906484"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF02943243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"volume-title":"Discrete-Time Signal Processing","year":"1999","author":"Oppenheim","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/97.681427"},{"key":"ref43","first-page":"223","article-title":"The CMU arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek","year":"2004"},{"article-title":"The LJ speech dataset","year":"2017","author":"Ito","key":"ref44"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"Paszke","key":"ref45"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09670741.pdf?arnumber=9670741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:34:43Z","timestamp":1705185283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9670741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3140480","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2022]]}}}