{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T17:47:46Z","timestamp":1774806466480,"version":"3.50.1"},"reference-count":37,"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\/icassp49660.2025.10890561","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":["MQAD: A Large-Scale Question Answering Dataset for Training Music Large Language Models"],"prefix":"10.1109","author":[{"given":"Zhihao","family":"Ouyang","sequence":"first","affiliation":[{"name":"ByteDance"}]},{"given":"Ju-Chiang","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Daiyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Bin","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Shangjie","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Quan","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref2","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref3","article-title":"Visual instruction tuning","volume-title":"NeurIPS","volume":"36","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"ref5","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","author":"Yang","year":"2023"},{"key":"ref6","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref7","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref8","article-title":"Are emergent abilities of large language models a mirage?","volume":"36","author":"Schaeffer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref10","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref11","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref12","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref13","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref14","article-title":"LLark: A multimodal foundation model for music","author":"Gardner","year":"2023"},{"key":"ref15","article-title":"LP-MusicCaps: LLM-based pseudo music captioning","volume-title":"ISMIR","author":"Doh"},{"key":"ref16","article-title":"The million song dataset","volume-title":"ISMIR","author":"Bertin-Mahieux"},{"key":"ref17","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.363"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/feduc.2023.1272229"},{"key":"ref21","article-title":"Large language models are human-level prompt engineers","author":"Zhou","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2713830"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747048"},{"key":"ref26","article-title":"SpecTNT: A time-frequency transformer for music audio","volume-title":"ISMIR","author":"Lu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096688"},{"key":"ref29","volume-title":"Tempo, Beat and Downbeat Estimation","author":"Matthew","year":"2021"},{"key":"ref30","article-title":"20 years of automatic chord recognition from audio","volume-title":"ISMIR","author":"Pauwels"},{"key":"ref31","article-title":"MuSFA: Improving music structural function analysis with partially labeled data","author":"Wang","year":"2022","journal-title":"ISMIR Late Breaking & Demo"},{"key":"ref32","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref36","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref37","article-title":"LoRa: Low-rank adaptation of large language models","author":"Hu","year":"2021"}],"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\/10890561.pdf?arnumber=10890561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:19Z","timestamp":1774416019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890561","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}