LeVo: High-Quality Song Generation with Multi-Preference Alignment

• URL: http://arxiv.org/abs/2506.07520v2
• Date: Sun, 15 Jun 2025 13:36:33 GMT
• Title: LeVo: High-Quality Song Generation with Multi-Preference Alignment
• Authors: Shun Lei, Yaoxun Xu, Zhiwei Lin, Huaicheng Zhang, Wei Tan, Hangting Chen, Jianwei Yu, Yixuan Zhang, Chenyu Yang, Haina Zhu, Shuai Wang, Zhiyong Wu, Dong Yu,
• Abstract summary: We introduce LeVo, an LM-based framework consisting of LeLM and a music accompaniment.<n>LeVo is capable of parallelly modeling two types of tokens: mixed tokens, which represent the combined audio of vocals and to achieve vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment.<n> Experimental results demonstrate that LeVo consistently outperforms existing methods on both objective and subjective metrics.
• Score: 49.94713419553945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in sound quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, an LM-based framework consisting of LeLM and a music codec. LeLM is capable of parallelly modeling two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and DPO post-training. Experimental results demonstrate that LeVo consistently outperforms existing methods on both objective and subjective metrics. Ablation studies further justify the effectiveness of our designs. Audio examples are available at https://levo-demo.github.io/. Code is released at https://github.com/tencent-ailab/songgeneration.

Related papers

• FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing [78.83988199306901]
  Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects.<n>Existing methods focus primarily on reducing the word error rate while ignoring the importance of lip-sync and acoustic quality.<n>We propose FlowDubber, which achieves high-quality audio-visual sync and pronunciation by incorporating a large speech language model and dual contrastive aligning.
  arXiv  Detail & Related papers  (2025-05-02T13:30:19Z)
• Make Some Noise: Towards LLM audio reasoning and generation using sound tokens [19.48089933713418]
  We introduce a novel approach that combines Variational Quantization with Flow Matching to convert audio into ultra-low discrete tokens of 0.23kpbs.<n>Our tokenizer outperforms a traditional VQ-VAE across various datasets with diverse acoustic events.
  arXiv  Detail & Related papers  (2025-03-28T09:43:47Z)
• SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation [75.86473375730392]
  SongGen is a fully open-source, single-stage auto-regressive transformer for controllable song generation.<n>It supports two output modes: mixed mode, which generates a mixture of vocals and accompaniment directly, and dual-track mode, which synthesizes them separately.<n>To foster community engagement and future research, we will release our model weights, training code, annotated data, and preprocessing pipeline.
  arXiv  Detail & Related papers  (2025-02-18T18:52:21Z)
• C3LLM: Conditional Multimodal Content Generation Using Large Language Models [66.11184017840688]
  We introduce C3LLM, a novel framework combining three tasks of video-to-audio, audio-to-text, and text-to-audio together. C3LLM adapts the Large Language Model (LLM) structure as a bridge for aligning different modalities. Our method combines the previous tasks of audio understanding, video-to-audio generation, and text-to-audio generation together into one unified model.
  arXiv  Detail & Related papers  (2024-05-25T09:10:12Z)
• MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies [32.482588500419006]
  We build a state-of-the-art text-to-music model, MusicLDM, that adapts Stable Diffusion and AudioLDM architectures to the music domain. We propose two different mixup strategies for data augmentation: beat-synchronous audio mixup and beat-synchronous latent mixup. In addition to popular evaluation metrics, we design several new evaluation metrics based on CLAP score to demonstrate that our proposed MusicLDM and beat-synchronous mixup strategies improve both the quality and novelty of generated music.
  arXiv  Detail & Related papers  (2023-08-03T05:35:37Z)
• Simple and Controllable Music Generation [94.61958781346176]
  MusicGen is a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns.
  arXiv  Detail & Related papers  (2023-06-08T15:31:05Z)
• Efficient Neural Music Generation [42.39082326446739]
  We present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform.
  arXiv  Detail & Related papers  (2023-05-25T05:02:35Z)
• Unsupervised Cross-Domain Singing Voice Conversion [105.1021715879586]
  We present a wav-to-wav generative model for the task of singing voice conversion from any identity. Our method utilizes both an acoustic model, trained for the task of automatic speech recognition, together with melody extracted features to drive a waveform-based generator.
  arXiv  Detail & Related papers  (2020-08-06T18:29:11Z)

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.