{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:32:16Z","timestamp":1776108736880,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen S&T Research Program","award":["GXWD20201231165807007-20200814115301001"],"award-info":[{"award-number":["GXWD20201231165807007-20200814115301001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3268730","type":"journal-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T18:25:13Z","timestamp":1682706313000},"page":"1720-1733","source":"Crossref","is-referenced-by-count":153,"title":["Diffsound: Discrete Diffusion Model for Text-to-Sound Generation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8905-224X","authenticated-orcid":false,"given":"Dongchao","family":"Yang","sequence":"first","affiliation":[{"name":"Advanced Data and Signal Processing Laboratory and School of Electronic and Computer Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-1436","authenticated-orcid":false,"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6088-0378","authenticated-orcid":false,"given":"Helin","family":"Wang","sequence":"additional","affiliation":[{"name":"Advanced Data and Signal Processing Laboratory and School of Electronic and Computer Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1707-0163","authenticated-orcid":false,"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Advanced Data and Signal Processing Laboratory and School of Electronic and Computer Engineering, Peking University, Beijing, China"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-6140","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"Advanced Data and Signal Processing Laboratory and School of Electronic and Computer Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-6844","authenticated-orcid":false,"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Bellevue, WA, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref57","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref12","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"austin","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref56","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref15","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"heusel","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref58","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref53","first-page":"211","article-title":"Audio captioning transformer","author":"mei","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref11","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"0","journal-title":"Proc Int Conf Ad Neural Inf Process Syst"},{"key":"ref54","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","author":"anderson","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref16","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17559"},{"key":"ref18","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref45","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref47","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref41","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref8","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume":"1","author":"kim","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref7","first-page":"6309","article-title":"Neural discrete representation learning","volume":"30","author":"oord","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref4","first-page":"1","article-title":"Conditional sound generation using neural discrete time-frequency representation learning","author":"liu","year":"0","journal-title":"Proc IEEE Int Workshop Mach Learn Signal Process"},{"key":"ref3","first-page":"1","article-title":"Taming visually guided sound generation","author":"iashin","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref6","first-page":"14910","article-title":"Mel-GAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683727"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref34","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","first-page":"1","article-title":"PriorGrad: Improving conditional denoising diffusion models with data-driven adaptive prior","author":"lee","year":"0","journal-title":"Poc Int Conf Learn Representations"},{"key":"ref36","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","author":"popov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"3518","article-title":"ImageBART: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume":"34","author":"esser","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref33","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"3518-3532","article-title":"Diffusion models beat GANS on image synthesis","volume":"34","author":"dhariwal","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref39","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref38","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume":"34","author":"hoogeboom","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018","journal-title":"Preprint"},{"key":"ref26","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume":"34","author":"ding","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"},{"key":"ref22","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref21","article-title":"DrumGAN: Synthesis of drum sounds with timbral feature conditioning using generative adversarial networks","author":"hurle","year":"0","journal-title":"Proc 21st Int Soc Music Inform Retrieval Conf (ISMIR)"},{"key":"ref28","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume":"32","author":"razavi","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with clip latents","author":"ramesh","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10112585.pdf?arnumber=10112585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:22:08Z","timestamp":1686594128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10112585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3268730","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}