MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
This addresses the problem of integrating music and text for applications like captioning and Q&A, but it is incremental as it builds on existing pre-trained models and datasets.
The paper tackles the gap between music and text by introducing MusiLingo, a system for music captioning and query response, which achieves competitive performance in generating captions and Q&A pairs, with a new dataset enabling notable advancements.
Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcity of high-quality music Q&A datasets, we created the MusicInstruct (MI) dataset from captions in the MusicCaps datasets, tailored for open-ended music inquiries. Empirical evaluations demonstrate its competitive performance in generating music captions and composing music-related Q&A pairs. Our introduced dataset enables notable advancements beyond previous ones.