{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:28Z","timestamp":1774419928092,"version":"3.50.1"},"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\/icassp49660.2025.10889233","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Generating Vocals from Lyrics and Musical Accompaniment"],"prefix":"10.1109","author":[{"given":"Georg","family":"Streich","sequence":"first","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca A.","family":"Lanzend\u00f6rfer","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Gr\u00f6tschla","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roger","family":"Wattenhofer","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Suno"},{"key":"ref2","volume-title":"Udio"},{"key":"ref3","article-title":"Riffusion - Stable diffusion for real-time music generation","author":"Forsgren","year":"2022"},{"key":"ref4","article-title":"Sonauto","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref6","author":"Shen","year":"2023","journal-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-678"},{"key":"ref9","article-title":"Snac: Multi-scale neural audio codec","volume-title":"Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation","author":"Siuzdak"},{"key":"ref10","author":"Dhariwal","year":"2020","journal-title":"Jukebox: A generative model for music"},{"key":"ref11","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","author":"Nistal","year":"2024","journal-title":"Diff-a-riff: Musical accompaniment co-creation via latent diffusion models"},{"key":"ref13","author":"Donahue","year":"2023","journal-title":"Singsong: Generating musical accompaniments from singing"},{"key":"ref14","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref16","author":"D\u00e9fossez","year":"2022","journal-title":"High fidelity neural audio compression"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","volume":"10","author":"Radford","year":"2022","journal-title":"Robust speech recognition via large-scale weak supervision. arxiv 2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-555"},{"key":"ref22","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref24","author":"Wang","year":"2023","journal-title":"Mel-band ro-former for music source separation"},{"key":"ref25","author":"Yang","year":"2022","journal-title":"Tensor programs v: Tuning large neural networks via zero-shot hyperparameter transfer"},{"key":"ref26","author":"Kilgour","year":"2018","journal-title":"Fr\\\u2019echet audio distance: A metric for evaluating music enhancement algorithms"},{"key":"ref27","author":"Kaplan","year":"2020","journal-title":"Scaling laws for neural language models"},{"key":"ref28","volume-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref29","article-title":"From discrete tokens to high-fidelity audio using multi-band diffusion","volume":"36","author":"Roman","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/10889233.pdf?arnumber=10889233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:29Z","timestamp":1774416329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889233","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}