{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:14:30Z","timestamp":1776885270643,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230964","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation"],"prefix":"10.1109","author":[{"given":"Sonal","family":"Kumar","sequence":"first","affiliation":[{"name":"Adobe Research,San Frnacisco,CA,USA"}]},{"given":"Prem","family":"Seetharaman","sequence":"additional","affiliation":[{"name":"Adobe Research,San Frnacisco,CA,USA"}]},{"given":"Justin","family":"Salamon","sequence":"additional","affiliation":[{"name":"Adobe Research,San Frnacisco,CA,USA"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Oriol","family":"Nieto","sequence":"additional","affiliation":[{"name":"Adobe Research,San Frnacisco,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref2","first-page":"21 450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Liu"},{"key":"ref3","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref5","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Compa: Addressing the gap in compositional reasoning in audio-language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ghosh"},{"key":"ref7","article-title":"A demand-driven perspective on generative audio ai","author":"Oh","year":"2023"},{"key":"ref8","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref10","article-title":"Fr\u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"ref11","article-title":"Generative adversarial nets","volume-title":"Neural Information Processing Systems","author":"Goodfellow","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref13","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref14","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref15","article-title":"Autoregressive diffusion transformer for text-to-speech synthesis","author":"Liu","year":"2024"},{"key":"ref16","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref18","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"Hsu","year":"2018"},{"key":"ref19","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Ar\u0131k"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888184"},{"key":"ref21","first-page":"6288","article-title":"GAMA: A large audio-language model with advanced audio understanding and complex reasoning abilities","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Ghosh"},{"key":"ref22","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1163\/9789004658820"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"issue":"70","key":"ref26","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Kumar"},{"issue":"140","key":"ref28","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref33","first-page":"13 916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230964.pdf?arnumber=11230964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:38:38Z","timestamp":1763404718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230964","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}