{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:17:23Z","timestamp":1783995443328,"version":"3.55.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248160","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:37Z","timestamp":1694799097000},"page":"1-5","source":"Crossref","is-referenced-by-count":18,"title":["CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models"],"prefix":"10.1109","author":[{"given":"Hao-Wen","family":"Dong","sequence":"first","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi","family":"Pons","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gautam","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santiago","family":"Pascual","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joan","family":"Serr\u00e0","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taylor","family":"Berg-Kirkpatrick","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language Models are Unsupervised Multitask Learners","author":"Radford","year":"2019","journal-title":"Technical Report of OpenAI"},{"key":"ref2","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref5","article-title":"MuLan: A Joint Embedding of Music Audio and Natural Language","volume-title":"Proc. ISMIR","author":"Huang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref8","article-title":"AudioGen: Textually Guided Audio Generation","volume-title":"Proc. ICLR","author":"Kreuk"},{"key":"ref9","article-title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref10","article-title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref11","article-title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","author":"Huang","year":"2023"},{"key":"ref12","article-title":"MusicLM: Generating Music From Text","author":"Agostinelli","year":"2023"},{"key":"ref13","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS 2022 Datasets and Benchmarks","author":"Schuhmann"},{"key":"ref14","article-title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref15","article-title":"Improved Denoising Diffusion Probabilistic Models","volume-title":"Proc. ICML","author":"Nichol"},{"key":"ref16","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref17","article-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","author":"Ramesh","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref19","article-title":"Taming Visually Guided Sound Generation","volume-title":"Proc. BMVC","author":"Iashin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref21","article-title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","volume-title":"Proc. ICLR","author":"Dong"},{"key":"ref22","article-title":"CLIPSynth: Learning Text-to-audio Synthesis from Videos Using CLIP and Diffusion Models","volume-title":"CVPR Workshop on Sight and Sound","author":"Dong"},{"key":"ref23","article-title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref25","article-title":"Classifier-Free Diffusion Guidance","volume-title":"NeurIPS Workshop on Deep Generative Models and Down-stream Applications","author":"Jonathan Ho"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1312"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2023,10,22]]},"end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248160.pdf?arnumber=10248160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T01:17:54Z","timestamp":1709342274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248160","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}