{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T10:43:41Z","timestamp":1769856221286,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096710","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":14,"title":["LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Jie","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xingchen","family":"Song","sequence":"additional","affiliation":[{"name":"Horizon Robotics,Beijing,China"}]},{"given":"Zhendong","family":"Peng","sequence":"additional","affiliation":[{"name":"Horizon Robotics,Beijing,China"}]},{"given":"Binbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics,Beijing,China"}]},{"given":"Fuping","family":"Pan","sequence":"additional","affiliation":[{"name":"Horizon Robotics,Beijing,China"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"13963","article-title":"Portaspeech: Portable and high-quality generative text-to-speech","author":"ren","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Devicetts: A small-footprint, fast, stable network for on-device text-to-speech","volume":"abs 2010 15311","author":"huang","year":"2020","journal-title":"CoRR"},{"key":"ref15","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume":"37","author":"sohl-dickstein","year":"2015","journal-title":"ICML"},{"key":"ref31","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref30","first-page":"1352","article-title":"Rezero is all you need: fast convergence at large depth","author":"bachlechner","year":"2021","journal-title":"Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence UAI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414870"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref32","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"ICLRE"},{"key":"ref16","article-title":"Diffusion models beat gans on image synthesis","author":"dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume":"139","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref18","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref24","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"ICLRE"},{"key":"ref23","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"popov","year":"2022","journal-title":"ICLRE"},{"key":"ref26","article-title":"Dpm-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume":"abs 2206 927","author":"lu","year":"2022","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref28","article-title":"Mish: A self regularized non-monotonic activation function","author":"misra","year":"2020","journal-title":"31 st British Machine Vision Conference 2020 BMVC 2020"},{"key":"ref27","first-page":"2022","article-title":"High quality streaming speech synthesis with low, sentence-length-independent latency","author":"ellinas","year":"2020","journal-title":"InterSpeech"},{"key":"ref29","first-page":"3530","article-title":"Efficient attention: Attention with linear complexities","author":"shen","year":"2021","journal-title":"IEEE Winter Conference on Applications of Computer Vision WACV"},{"key":"ref8","first-page":"7472","article-title":"Improving fastspeech TTS with efficient self-attention and compact feedforward network","author":"xiao","year":"2022","journal-title":"ICASSP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414400"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413373"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"key":"ref3","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref5","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096710.pdf?arnumber=10096710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T22:27:10Z","timestamp":1698100030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096710","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}