{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:16:41Z","timestamp":1776885401573,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890164","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models"],"prefix":"10.1109","author":[{"given":"Purnima","family":"Kamath","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chitralekha","family":"Gupta","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suranga","family":"Nanayakkara","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sound Modelling and Morphing","author":"Fitz","year":"2007"},{"key":"ref2","article-title":"Morphing isolated quasi-harmonic acoustic musical instrument sounds guided by perceptually motivated features","volume-title":"Ph.D. thesis","author":"Caetano","year":"2011"},{"key":"ref3","article-title":"Sound morphing by audio descriptors and parameter interpolation","volume-title":"Proceedings of the 19th International Conference on Digital Audio Effects (DAFx-16)","author":"Kazazis"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Audi-oldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70210-6_31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543292"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-791"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096328"},{"key":"ref12","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-03789-4_20"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/23311835.2015.1102116"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref19","first-page":"17022","article-title":"Hifigan: 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":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","article-title":"Scaling instruction-finetuned language models","author":"Chung"},{"key":"ref22","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0137-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","article-title":"A formal evaluation framework for sound morphing","volume-title":"ICMC","author":"Caetano"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref29","article-title":"Parameter sensitivity of deep-feature based evaluation metrics for audio textures","author":"Gupta","year":"2022"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890164.pdf?arnumber=10890164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:19Z","timestamp":1774416259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890164","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}