YuE: Scaling Open Foundation Models for Long-Form Music Generation

• URL: http://arxiv.org/abs/2503.08638v1
• Date: Tue, 11 Mar 2025 17:26:50 GMT
• Title: YuE: Scaling Open Foundation Models for Long-Form Music Generation
• Authors: Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du, Xinrun Du, Zhen Ye, Tianyu Zheng, Yinghao Ma, Minghao Liu, Zeyue Tian, Ziya Zhou, Liumeng Xue, Xingwei Qu, Yizhi Li, Shangda Wu, Tianhao Shen, Ziyang Ma, Jun Zhan, Chunhui Wang, Yatian Wang, Xiaowei Chi, Xinyue Zhang, Zhenzhu Yang, Xiangzhou Wang, Shansong Liu, Lingrui Mei, Peng Li, Junjie Wang, Jianwei Yu, Guojian Pang, Xu Li, Zihao Wang, Xiaohuan Zhou, Lijun Yu, Emmanouil Benetos, Yong Chen, Chenghua Lin, Xie Chen, Gus Xia, Zhaoxiang Zhang, Chao Zhang, Wenhu Chen, Xinyu Zhou, Xipeng Qiu, Roger Dannenberg, Jiaheng Liu, Jian Yang, Wenhao Huang, Wei Xue, Xu Tan, Yike Guo,
• Abstract summary: YuE is a family of open foundation models based on the LLaMA2 architecture.<n>It generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment.
• Score: 134.54174498094565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation

Related papers

• CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation [17.41880273107978]
  Contrastive Long-form Language-Audio Pretraining (textbfCoLLAP) We propose Contrastive Long-form Language-Audio Pretraining (textbfCoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words) We collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds.
  arXiv  Detail & Related papers  (2024-10-03T07:46:51Z)
• SongCreator: Lyrics-based Universal Song Generation [53.248473603201916]
  SongCreator is a song-generation system designed to tackle the challenge of generating songs with both vocals and accompaniment given lyrics. The model features two novel designs: a meticulously designed dual-sequence language model (M) to capture the information of vocals and accompaniment for song generation, and a series of attention mask strategies for DSLM. Experiments demonstrate the effectiveness of SongCreator by achieving state-of-the-art or competitive performances on all eight tasks.
  arXiv  Detail & Related papers  (2024-09-09T19:37:07Z)
• Practical and Reproducible Symbolic Music Generation by Large Language Models with Structural Embeddings [28.685224087199053]
  Music generation introduces challenging complexities to large language models. Existing works share three major drawbacks: 1) their tokenization requires domain-specific annotations, such as bars and beats, that are typically missing in raw MIDI data. We develop a MIDI-based music generation framework inspired by MuseNet, empirically studying two structural embeddings that do not rely on domain-specific annotations.
  arXiv  Detail & Related papers  (2024-07-29T11:24:10Z)
• MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation [18.181382408551574]
  We propose a novel task of Colloquial Description-to-Song Generation. It focuses on aligning the generated content with colloquial human expressions. This task is aimed at bridging the gap between colloquial language understanding and auditory expression within an AI model.
  arXiv  Detail & Related papers  (2024-07-03T15:12:36Z)
• MuPT: A Generative Symbolic Music Pretrained Transformer [56.09299510129221]
  We explore the application of Large Language Models (LLMs) to the pre-training of music. To address the challenges associated with misaligned measures from different tracks during generation, we propose a Synchronized Multi-Track ABC Notation (SMT-ABC Notation) Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set.
  arXiv  Detail & Related papers  (2024-04-09T15:35:52Z)
• SongComposer: A Large Language Model for Lyric and Melody Composition in Song Generation [88.33522730306674]
  SongComposer could understand and generate melodies and lyrics in symbolic song representations. We resort to symbolic song representation, the mature and efficient way humans designed for music. With extensive experiments, SongComposer demonstrates superior performance in lyric-to-melody generation, melody-to-lyric generation, song continuation, and text-to-song creation.
  arXiv  Detail & Related papers  (2024-02-27T16:15:28Z)
• JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models [16.18987351077676]
  This paper introduces JEN-1, a universal high-fidelity model for text-to-music generation. JEN-1 is a diffusion model incorporating both autoregressive and non-autoregressive training. Evaluations demonstrate JEN-1's superior performance over state-of-the-art methods in text-music alignment and music quality.
  arXiv  Detail & Related papers  (2023-08-09T06:27:24Z)
• Unsupervised Melody-to-Lyric Generation [91.29447272400826]
  We propose a method for generating high-quality lyrics without training on any aligned melody-lyric data. We leverage the segmentation and rhythm alignment between melody and lyrics to compile the given melody into decoding constraints. Our model can generate high-quality lyrics that are more on-topic, singable, intelligible, and coherent than strong baselines.
  arXiv  Detail & Related papers  (2023-05-30T17:20:25Z)
• Melody-Conditioned Lyrics Generation with SeqGANs [81.2302502902865]
  We propose an end-to-end melody-conditioned lyrics generation system based on Sequence Generative Adversarial Networks (SeqGAN) We show that the input conditions have no negative impact on the evaluation metrics while enabling the network to produce more meaningful results.
  arXiv  Detail & Related papers  (2020-10-28T02:35:40Z)
• Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions [14.786601824794369]
  We present a model for composing melodies given a user specified symbolic scenario combined with a previous music context. Our model is capable of generating long melodies by regarding 8-beat note sequences as basic units, and shares consistent rhythm pattern structure with another specific song. Results show that the music generated by our model tends to have salient repetition structures, rich motives, and stable rhythm patterns.
  arXiv  Detail & Related papers  (2020-02-05T06:23:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.