{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:38:08Z","timestamp":1777477088045,"version":"3.51.4"},"reference-count":26,"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\/icassp49660.2025.10890334","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":5,"title":["Text2FX: Harnessing CLAP Embeddings for Text-Guided Audio Effects"],"prefix":"10.1109","author":[{"given":"Annie","family":"Chu","sequence":"first","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"O\u2019Reilly","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"Barnett","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Pardo","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0023"},{"issue":"6","key":"ref2","first-page":"419","article-title":"Weighted-function-based rapid mapping of descriptors to audio processing parameters","volume":"59","author":"Sabin","year":"2011","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2016.0037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967207"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967238"},{"key":"ref6","article-title":"Word based end-to-end real time neural audio effects for equalisation","volume-title":"Audio Engineering Society Convention 155.","author":"Balasubramaniam","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref8","article-title":"Creative text-to-audio generation via synthesizer programming","author":"Cherep","year":"2024"},{"key":"ref9","article-title":"Ddsp: Differentiable digital signal processing","volume-title":"International Conference on Learning Representations","author":"Engel"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2023.1284100"},{"key":"ref11","article-title":"Speech synthesis and control using differentiable dsp","author":"Fabbro","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0025"},{"key":"ref13","article-title":"Diff-mst: Differentiable mixing style transfer","author":"Vanka","year":"2024","journal-title":"ISMIR"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP43922.2022.9747909","article-title":"Source separation by steering pretrained music models","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Manilow"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref16","article-title":"St-ito: Controlling audio effects for style transfer with inference-time optimization","author":"Steinmetz","year":"2024","journal-title":"ISMIR"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref19","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref20","first-page":"468","article-title":"Vocalset: A singing voice dataset","author":"Wilkins","year":"2018","journal-title":"ISMIR"},{"key":"ref21","first-page":"219","article-title":"Automatic tablature transcription of electric guitar recordings by estimation of score-and instrument-related parameters","author":"Kehling","year":"2014","journal-title":"DAFx"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2379648"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","article-title":"Correlations between objective and subjective evaluations of music source separation","author":"RUMBOLD","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2019.36.5.457"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"}],"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\/10890334.pdf?arnumber=10890334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:59Z","timestamp":1774416119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890334","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}