{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:49:06Z","timestamp":1778860146784,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447251","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10736-10740","source":"Crossref","is-referenced-by-count":11,"title":["Fregrad: Lightweight and Fast Frequency-Aware Diffusion Vocoder"],"prefix":"10.1109","author":[{"given":"Tan Dat","family":"Nguyen","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjoon","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref3","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref4","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","author":"Choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref7","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"Kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref9","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","volume-title":"Proc. ICLR","author":"Mehri"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","article-title":"WaveFlow: A compact flow-based model for raw audio","volume-title":"Proc. ICML","author":"Ping"},{"key":"ref12","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"Kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref13","article-title":"GANSynth: Adversarial neural audio synthesis","volume-title":"Proc. ICLR","author":"Engel"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2906484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref17","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref18","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref20","article-title":"PriorGrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref21","article-title":"BDDM: Bilateral denoising diffusion models for fast and high-quality speech synthesis","volume-title":"Proc. ICLR","author":"Lam"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095749"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746690"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1063\/1.4823127"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref27","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/83.908504"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/bf01456326"},{"key":"ref31","article-title":"Simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. ICML","author":"Hoogeboom"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447251.pdf?arnumber=10447251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:44:01Z","timestamp":1722573841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447251","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}