QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation

• URL: http://arxiv.org/abs/2405.15863v2
• Date: Tue, 20 Aug 2024 04:54:40 GMT
• Title: QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation
• Authors: Chang Li, Ruoyu Wang, Lijuan Liu, Jun Du, Yixuan Sun, Zilu Guo, Zhenrong Zhang, Yuan Jiang,
• Abstract summary: We propose a novel paradigm for high-quality music generation that incorporates a quality-aware training strategy. We first adapted and implemented a masked diffusion transformer (MDT) model for the TTM task, demonstrating its capacity for quality control and enhanced musicality. Experiments demonstrate our state-of-the-art (SOTA) performance on MusicCaps and the Song-Describer dataset.
• Score: 46.301388755267986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, diffusion-based text-to-music (TTM) generation has gained prominence, offering an innovative approach to synthesizing musical content from textual descriptions. Achieving high accuracy and diversity in this generation process requires extensive, high-quality data, including both high-fidelity audio waveforms and detailed text descriptions, which often constitute only a small portion of available datasets. In open-source datasets, issues such as low-quality music waveforms, mislabeling, weak labeling, and unlabeled data significantly hinder the development of music generation models. To address these challenges, we propose a novel paradigm for high-quality music generation that incorporates a quality-aware training strategy, enabling generative models to discern the quality of input music waveforms during training. Leveraging the unique properties of musical signals, we first adapted and implemented a masked diffusion transformer (MDT) model for the TTM task, demonstrating its distinct capacity for quality control and enhanced musicality. Additionally, we address the issue of low-quality captions in TTM with a caption refinement data processing approach. Experiments demonstrate our state-of-the-art (SOTA) performance on MusicCaps and the Song-Describer Dataset. Our demo page can be accessed at https://qa-mdt.github.io/.

Related papers

• 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. It supports two output modes: mixed mode, which generates a mixture of vocals and accompaniment directly, and dual-track mode, which synthesizes them separately. 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)
• Efficient Fine-Grained Guidance for Diffusion-Based Symbolic Music Generation [14.156461396686248]
  We introduce an efficient Fine-Grained Guidance (FGG) approach within diffusion models. FGG guides the diffusion models to generate music that aligns more closely with the control and intent of expert composers. This approach empowers diffusion models to excel in advanced applications such as improvisation, and interactive music creation.
  arXiv  Detail & Related papers  (2024-10-11T00:41:46Z)
• 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)
• StemGen: A music generation model that listens [9.489938613869864]
  We present an alternative paradigm for producing music generation models that can listen and respond to musical context. We describe how such a model can be constructed using a non-autoregressive, transformer-based model architecture. The resulting model reaches the audio quality of state-of-the-art text-conditioned models, as well as exhibiting strong musical coherence with its context.
  arXiv  Detail & Related papers  (2023-12-14T08:09:20Z)
• 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)
• MARBLE: Music Audio Representation Benchmark for Universal Evaluation [79.25065218663458]
  We introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines.
  arXiv  Detail & Related papers  (2023-06-18T12:56:46Z)
• 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)
• ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models [67.66825818489406]
  This paper introduces a text-to-waveform music generation model, underpinned by the utilization of diffusion models. Our methodology hinges on the innovative incorporation of free-form textual prompts as conditional factors to guide the waveform generation process. We demonstrate that our generated music in the waveform domain outperforms previous works by a large margin in terms of diversity, quality, and text-music relevance.
  arXiv  Detail & Related papers  (2023-02-09T06:27:09Z)

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.