{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:50Z","timestamp":1775230190838,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447027","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"286-290","source":"Crossref","is-referenced-by-count":25,"title":["Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning"],"prefix":"10.1109","author":[{"given":"Shansong","family":"Liu","sequence":"first","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Atin Sakkeer","family":"Hussain","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Chenshuo","family":"Sun","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Simple and Controllable Music Generation","author":"Copet","year":"2023"},{"key":"ref2","article-title":"Jukebox: A Generative Model for Music","author":"Dhariwal","year":"2020"},{"key":"ref3","article-title":"Mo\u00fbsai: Text-to-Music Generation with Long-Context Latent Diffusion","author":"Schneider","year":"2023"},{"key":"ref4","article-title":"MusicLM: Generating Music From Text","author":"Agostinelli","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533461"},{"key":"ref6","article-title":"Audio Captioning Transformer","author":"Mei","year":"2021"},{"key":"ref7","article-title":"The SJTU System for DCASE2022 Challenge Task 6: Audio Captioning with Audiotext Retrieval Pre-training","volume-title":"Tech. Rep., DCASE2022 Challenge","author":"Xu","year":"2022"},{"key":"ref8","article-title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","author":"Doh","year":"2023"},{"key":"ref9","article-title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","author":"Zhang","year":"2023"},{"key":"ref10","article-title":"Unified Model for Image, Video, Audio and Language Tasks","author":"Shukor","year":"2023"},{"key":"ref11","article-title":"Listen, Think, and Understand","author":"Gong","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref13","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref14","article-title":"LLaMA 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW56448.2022.9859499"},{"key":"ref16","first-page":"387","article-title":"Evaluation of Algorithms Using Games: The Case of Music Tagging","volume-title":"ISMIR","author":"Law","year":"2009"},{"key":"ref17","year":"2023","journal-title":"Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs"},{"key":"ref18","first-page":"88","article-title":"Codified Audio Language Modeling Learns Useful Representations for Music Information Retrieval","author":"Castellon","year":"2021","journal-title":"ISMIR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref22","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision","volume-title":"ICML","author":"Radford"},{"key":"ref23","article-title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","author":"Li","year":"2023"},{"key":"ref24","article-title":"Robust Vector Quantized-Variational Autoencoder","author":"Lai","year":"2022"},{"key":"ref25","first-page":"3","article-title":"Constant-Q Transform Toolbox for Music Processing","author":"Sch\u00f6rkhuber","year":"2010","journal-title":"SMC"},{"key":"ref26","first-page":"88","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"Castellon","year":"2021","journal-title":"ISMIR"},{"key":"ref27","article-title":"The MTG-Jamendo Dataset for Automatic Music Tagging","author":"Bogdanov","year":"2019","journal-title":"ICML"},{"key":"ref28","first-page":"311","article-title":"BLEU: A Method for Automatic Evaluation of Machine Translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref29","first-page":"65","article-title":"METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments","volume-title":"ACL Workshop","author":"Banerjee"},{"key":"ref30","first-page":"74","article-title":"ROUGE: A Package for Automatic Evaluation of Summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref31","article-title":"BERTScore: Evaluating Text Generation with BERT","author":"Zhang","year":"2020","journal-title":"ICLR"},{"key":"ref32","article-title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","author":"Gao","year":"2023"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447027.pdf?arnumber=10447027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:40:44Z","timestamp":1722573644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447027","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}