{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:29:46Z","timestamp":1768073386002,"version":"3.49.0"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448220","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6960-6964","source":"Crossref","is-referenced-by-count":4,"title":["Audio-Journey: Open Domain Latent Diffusion Based Text-To-Audio Generation"],"prefix":"10.1109","author":[{"given":"Jackson","family":"Michaels","sequence":"first","affiliation":[{"name":"Northwestern University,Chicago,IL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng B","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Yao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Yu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zach","family":"Wood-Doughty","sequence":"additional","affiliation":[{"name":"Northwestern University,Chicago,IL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref4","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"issue":"1","key":"ref5","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref7","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref8","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021"},{"key":"ref9","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2020"},{"key":"ref12","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref17","article-title":"An overview on the evaluated video retrieval tasks at trecvid 2022","volume-title":"Proceedings of TRECVID 2022","author":"Awad"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref20","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019","journal-title":"CoRR"},{"key":"ref21","article-title":"On the importance of noise scheduling for diffusion models","author":"Chen","year":"2023"},{"key":"ref22","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref23","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022"},{"key":"ref24","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","author":"Series","year":"2014","journal-title":"International Telecommunication Union Radiocommunication Assembly"},{"key":"ref25","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"}],"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\/10448220.pdf?arnumber=10448220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:42:39Z","timestamp":1722660159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448220","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}