{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:31:12Z","timestamp":1776889872442,"version":"3.51.2"},"reference-count":32,"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\/icassp49660.2025.10888854","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":1,"title":["Accompaniment Prompt Adherence: A measure for evaluating music accompaniment systems"],"prefix":"10.1109","author":[{"given":"Maarten","family":"Grachten","sequence":"first","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Nistal","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref2","article-title":"Riffusion - Stable diffusion for real-time music generation","author":"Forsgren","year":"2022"},{"key":"ref3","article-title":"Mo\u00fbsai: Text-to-Music Generation with Long-Context Latent Diffusion","author":"Schneider","year":"2023","journal-title":"CoRR"},{"key":"ref4","article-title":"Simple and Controllable Music Generation","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS","author":"Copet"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937261"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app10186627"},{"key":"ref7","article-title":"JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR","author":"Wu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446400"},{"key":"ref10","article-title":"Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models","volume-title":"Proceedings of the 25th International Society for Music Information Retrieval Conference, ISMIR","author":"Nistal"},{"key":"ref11","article-title":"Multi-source diffusion models for simultaneous music generation and separation","author":"Mariani","year":"2023"},{"key":"ref12","article-title":"Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation","author":"Tal","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref14","article-title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","volume-title":"Proceedings of the 25th International Society for Music Information Retrieval Conference, ISMIR","author":"Riou"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888146"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref18","article-title":"Samplematch: Drum sample retrieval by musical context","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR)","author":"Lattner"},{"key":"ref19","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref21","article-title":"pyloudnorm: A simple yet flexible loudness meter in python","author":"Steinmetz","year":"2021","journal-title":"150th AES Convention"},{"key":"ref22","article-title":"cylimiter: Python rate limiting library","author":"\u017belasko","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref24","article-title":"torchvggish: Pytorch implementation of vggish audio feature extractor","author":"Taylor","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref26","article-title":"openl3: Deep audio and music embedding tool","year":"2024"},{"key":"ref27","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref28","article-title":"CLAP: Contrastive Language-Audio Pretraining","year":"2024"},{"key":"ref29","article-title":"MUSDB18-HQ - an uncompressed version of MUSDB18","author":"Rafii","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.111.2.361"},{"key":"ref31","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref32","article-title":"High-fidelity audio compression with improved RVQGAN","volume":"36","author":"Kumar","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\/10888854.pdf?arnumber=10888854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:45Z","timestamp":1774416405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888854","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}