{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:06Z","timestamp":1764400566319,"version":"3.46.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62301521"],"award-info":[{"award-number":["62301521"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2308085QF200"],"award-info":[{"award-number":["2308085QF200"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249381","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"483-488","source":"Crossref","is-referenced-by-count":0,"title":["A Distilled Low-Latency Neural Vocoder with Explicit Amplitude and Phase Prediction"],"prefix":"10.1109","author":[{"given":"Hui-Peng","family":"Du","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Vocos: Closing the gap between timedomain and fourier-based neural vocoders for highquality audio synthesis","author":"Siuzdak","year":"2024","journal-title":"Proc. ICLR"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP49357.2023.10096390"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/LSP.2024.3439469"},{"key":"ref5","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"Mehri","year":"2017","journal-title":"Proc. ICLR"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref8","first-page":"7706","article-title":"WaveFlow: A compact flow-based model for raw audio","author":"Ping","year":"2020","journal-title":"Proc. ICML"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP48485.2024.10447251"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TASLP.2023.3277276"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TASLP.2024.3385285"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2024-1559"},{"key":"ref15","article-title":"Spectral codecs: Spectrogram-based audio codecs for high quality speech synthesis","author":"Langman","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1007\/978-981-97-0601-3_6"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref19","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"Lee","year":"2023","journal-title":"Proc. ICLR"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR52729.2023.01548"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TASLP.2024.3417347"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.21437\/Interspeech.2023-1157"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP49660.2025.10887678"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.21437\/Interspeech.2021-1016"},{"volume-title":"Superseded-CSTR VCTK corpus: English multispeaker corpus for cstr voice cloning toolkit","year":"2016","author":"Veaux","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.21437\/Interspeech.2022-439"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249381.pdf?arnumber=11249381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:50Z","timestamp":1764400310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249381","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}