{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:24:20Z","timestamp":1768073060093,"version":"3.49.0"},"reference-count":29,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096643","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Diverse and Vivid Sound Generation from Text Descriptions"],"prefix":"10.1109","author":[{"given":"Guangwei","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Lingfeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Onoma-to-wave: Environmental sound synthesis from onomatopoeic words","author":"okamoto","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011174"},{"key":"ref15","article-title":"Audiogen: Textually guided audio generation","author":"kreuk","year":"2022"},{"key":"ref14","article-title":"Diffsound: Discrete diffusion model for text-to-sound generation","author":"yang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref10","article-title":"Midinet: A convolutional generative adversarial network for symbolic-domain music generation","author":"yang","year":"2017"},{"key":"ref2","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"2021"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref16","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref26","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"The SJTU system for DCASE2022 challenge task 6: Audio captioning with audio-text retrieval pre-training","author":"xu","year":"2022","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref20","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013"},{"key":"ref22","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"johnson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref21","first-page":"1125","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref27","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1002\/grl.50288","article-title":"Gpt2: Empirical slant delay model for radio space geodetic techniques","volume":"40","author":"lagler","year":"2013","journal-title":"Geophysical Research Letters"},{"key":"ref8","article-title":"Close to human quality tts with transformer","author":"li","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref4","article-title":"Taming visually guided sound generation","author":"iashin","year":"2021"},{"key":"ref3","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"saharia","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052918"},{"key":"ref5","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume":"33","author":"su","year":"2020","journal-title":"Advances in neural information processing systems"}],"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\/10096643.pdf?arnumber=10096643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:54Z","timestamp":1699883994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096643","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}