# SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition Source: [SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:53:53.053Z Authors: Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang Published: 2024-02-27T16:15:28.000Z ## Abstract Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them. Despite achievements in sub-tasks such as lyric generation, lyric-to-melody, and melody-to-lyric, etc, a unified model for song composition has not yet been achieved. In this paper, we introduce SongComposer, a pioneering step towards a unified song composition model that can readily create symbolic lyrics and melodies following instructions. SongComposer is a music-specialized large language model (LLM) that, for the first time, integrates the capability of simultaneously composing lyrics and melodies into LLMs by leveraging three key innovations: 1) a flexible tuple format for word-level alignment of lyrics and melodies, 2) an extended tokenizer vocabulary for song notes, with scalar initialization based on musical knowledge to capture rhythm, and 3) a multi-stage pipeline that captures musical structure, starting with motif-level melody patterns and progressing to phrase-level structure for improved coherence. Extensive experiments demonstrate that SongComposer outperforms advanced LLMs, including GPT-4, in tasks such as lyric-to-melody generation, melody-to-lyric generation, song continuation, and text-to-song creation. Moreover, we will release SongCompose, a large-scale dataset for training, containing paired lyrics and melodies in Chinese and English. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Lyric-to-Melody generation on GTSinger English (test)](): Lyric-to-Melody generation; GTSinger English (test); Pitch Deviation (PD): 31.58. - [Lyric-to-Melody generation on GTSinger (test)](): Lyric-to-Melody generation; GTSinger (test); MOS: 2.92. ## Original sources and implementation [Original paper]() [PDF]()