{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:09:13Z","timestamp":1781334553358,"version":"3.54.1"},"reference-count":38,"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"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890522","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":3,"title":["LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment"],"prefix":"10.1109","author":[{"given":"Huan","family":"Zhang","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent K.M.","family":"Cheung","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayato","family":"Nishioka","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinichi","family":"Furuya","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081351"},{"key":"ref2","first-page":"637","article-title":"End-to-end learning for music audio tagging at scale","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR)","author":"Pons"},{"key":"ref3","article-title":"Leveraging hierarchical structures for few-shot musical instrument recognition","volume-title":"Proceedings of the 22th International Society for Music Information Retrieval Conference, ISMIR 2021","author":"Garcia"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"ref5","article-title":"LP-MusicCaps: LLM-based pseudo music captioning","volume-title":"Proceeding of the 24th International Society on Music Information Retrieval (ISMIR)","author":"Doh"},{"key":"ref6","article-title":"Llark: A multi-modal foundation model for music","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Gardner"},{"key":"ref7","article-title":"From audio encoders to piano judges: Benchmarking performance understanding for solo piano","volume-title":"Proceeding of the 25t International Society on Music Information Retrieval (ISMIR)","author":"Zhang"},{"key":"ref8","article-title":"Music performance analysis: A survey","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR)","author":"Lerch"},{"key":"ref9","article-title":"Learn by referencing: Towards deep metric learning for singing assessment","volume-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR)","author":"Zhang"},{"key":"ref10","article-title":"Score-informed networks for music performance assessment","volume-title":"Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR)","author":"Huang"},{"key":"ref11","article-title":"Improving music performance assessment with contrastive learning","volume-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR)","author":"Seshadri"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5220\/0009817006290640"},{"key":"ref13","article-title":"Simulating piano performance mistakes for music learning","volume-title":"Proceedings of the Sound and Music Computing Conference (SMC)","author":"Morsi"},{"key":"ref14","first-page":"1","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023"},{"key":"ref15","first-page":"4","article-title":"Towards audio language modeling - an overview","author":"Wu","year":"2024"},{"key":"ref16","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","author":"Deshmukh"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"issue":"2","key":"ref18","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","volume":"82","author":"Tang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref20","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of Machine Learning Research","volume":"202","author":"Radford"},{"key":"ref21","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.194"},{"key":"ref23","author":"Ma","year":"2024","journal-title":"Foundation models for music: A survey"},{"key":"ref24","article-title":"Expert and novice evaluations of piano performances : Criteria for computer-aided feedback","volume-title":"Proceeding of the 24th International Society on Music Information Retrieval (ISMIR)","author":"Jiang"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-35382-6_20","article-title":"CROCUS: Dataset of musical performance critiques","volume-title":"Proceedings of the International Symposium on Computer Music Multidisciplinary Research (CMMR)","author":"Matsubara"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3077981.3078032"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289901"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733638"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061267"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121776"},{"key":"ref31","article-title":"On the characterization of expressive performance in classical music: First results of the con espressione game","volume-title":"Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR)","author":"Cancino-Chac\u00f3n"},{"key":"ref32","article-title":"Sounds Out of Pl\u00e4ce? Score-independent detection of conspicuous mistakes in piano performances","volume-title":"Proceeding of the 24th International Society on Music Information Retrieval (ISMIR)","author":"Morsi"},{"key":"ref33","article-title":"ATEPP: A dataset of automatically transcribed expressive piano performance","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3533375"},{"key":"ref35","article-title":"Masked autoencoders that listen","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Hu"},{"key":"ref36","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","journal-title":"NeurIPS 2023 Datasets and Benchmarks Poster"},{"key":"ref37","article-title":"Listen, think, and understand","volume-title":"proceedings of the International Conference on Learning Representations (ICLR)","author":"Gong"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"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\/10890522.pdf?arnumber=10890522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:46Z","timestamp":1774416046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890522","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}