M$^{2}$UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models

TL;DR

The paper introduces M$^{2}$UGen, a framework that combines multi-modal understanding and music generation using large language models and pretrained models across text, images, videos, and audio, achieving state-of-the-art results.

Contribution

It presents a novel integrated framework for multi-modal music understanding and generation leveraging LLMs and pretrained models, filling a research gap in combined understanding and creation.

Findings

Achieves or surpasses current state-of-the-art performance.

Effectively integrates multi-modal data for music generation.

Supports diverse modalities including text, images, and videos.

Abstract

The current landscape of research leveraging large language models (LLMs) is experiencing a surge. Many works harness the powerful reasoning capabilities of these models to comprehend various modalities, such as text, speech, images, videos, etc. They also utilize LLMs to understand human intention and generate desired outputs like images, videos, and music. However, research that combines both understanding and generation using LLMs is still limited and in its nascent stage. To address this gap, we introduce a Multi-modal Music Understanding and Generation (M$^{2}$UGen) framework that integrates LLM's abilities to comprehend and generate music for different modalities. The M$^{2}$UGen framework is purpose-built to unlock creative potential from diverse sources of inspiration, encompassing music, image, and video through the use of pretrained MERT, ViT, and ViViT models, respectively. To enable music generation, we explore the use of AudioLDM 2 and MusicGen. Bridging multi-modal understanding and music generation is accomplished through the integration of the LLaMA 2 model. Furthermore, we make use of the MU-LLaMA model to generate extensive datasets that support text/image/video-to-music generation, facilitating the training of our M$^{2}$UGen framework. We conduct a thorough evaluation of our proposed framework. The experimental results demonstrate that our model achieves or surpasses the performance of the current state-of-the-art models.