Key points are not available for this paper at this time.
Text-to-music generation integrates natural language processing and music generation, enabling artificial intelligence (AI) to compose music from textual descriptions. While AI-enabled music generation has advanced, challenges in aligning text with musical structures remain underexplored. This paper systematically reviews text-to-music generation across symbolic and audio domains, covering melody composition, polyphony, instrumental synthesis, and singing voice generation. It categorizes existing methods into traditional, hybrid, and end-to-end LLM-centric frameworks according to the usage of large language models (LLMs), highlighting the growing role of LLMs in improving controllability and expressiveness. Despite progress, challenges such as data scarcity, representation limitations, and long-term coherence persist. Future work should enhance multi-modal integration, improve model generalization, and develop more user-controllable frameworks to advance AI-enabled music composition.
Zhao et al. (Tue,) studied this question.