Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion Model

• URL: http://arxiv.org/abs/2408.01950v1
• Date: Sun, 4 Aug 2024 07:38:38 GMT
• Title: Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion Model
• Authors: Shipei Liu, Xiaoya Fan, Guowei Wu,
• Abstract summary: Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes. We introduce the Music-Diff architecture, which fits a joint distribution of notes and semantic information to generate symbolic music conditionally.
• Score: 6.085444830169205
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue that the distribution of notes can be modeled by translational invariance and periodicity, especially using diffusion models to generalize notes by injecting frequency-domain Gaussian noise. However, due to the low-density nature of music symbols, estimating the distribution of notes latent in the high-density solution space poses significant challenges. To address this problem, we introduce the Music-Diff architecture, which fits a joint distribution of notes and accompanying semantic information to generate symbolic music conditionally. We first enhance the fragmentation module for extracting semantics by using event-based notations and the structural similarity index, thereby preventing boundary blurring. As a prerequisite for multivariate perturbation, we introduce a joint pre-training method to construct the progressions between notes and musical semantics while avoiding direct modeling of low-density notes. Finally, we recover the perturbed notes by a multi-branch denoiser that fits multiple noise objectives via Pareto optimization. Our experiments suggest that in contrast to language models, joint probability diffusion models perturbing at both note and semantic levels can provide more sample diversity and compositional regularity. The case study highlights the rhythmic advantages of our model over language- and DDPMs-based models by analyzing the hierarchical structure expressed in the self-similarity metrics.

Related papers

• Autoregressive Speech Synthesis without Vector Quantization [135.4776759536272]
  We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS) MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition.
  arXiv  Detail & Related papers  (2024-07-11T14:36:53Z)
• Glauber Generative Model: Discrete Diffusion Models via Binary Classification [21.816933208895843]
  We introduce the Glauber Generative Model (GGM), a new class of discrete diffusion models. GGM deploys a Markov chain to denoise a sequence of noisy tokens to a sample from a joint distribution of discrete tokens. We show that it outperforms existing discrete diffusion models in language generation and image generation.
  arXiv  Detail & Related papers  (2024-05-27T10:42:13Z)
• One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls [77.42510898755037]
  One More Step (OMS) is a compact network that incorporates an additional simple yet effective step during inference. OMS elevates image fidelity and harmonizes the dichotomy between training and inference, while preserving original model parameters. Once trained, various pre-trained diffusion models with the same latent domain can share the same OMS module.
  arXiv  Detail & Related papers  (2023-11-27T12:02:42Z)
• Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles [95.49699178874683]
  We propose DiffDiv, an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs) We show that DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features. We show that DPM-guided diversification is sufficient to remove dependence on shortcut cues, without a need for additional supervised signals.
  arXiv  Detail & Related papers  (2023-11-23T15:47:33Z)
• A Cheaper and Better Diffusion Language Model with Soft-Masked Noise [62.719656543880596]
  Masked-Diffuse LM is a novel diffusion model for language modeling, inspired by linguistic features in languages. Specifically, we design a linguistic-informed forward process which adds corruptions to the text through strategically soft-masking to better noise the textual data. We demonstrate that our Masked-Diffuse LM can achieve better generation quality than the state-of-the-art diffusion models with better efficiency.
  arXiv  Detail & Related papers  (2023-04-10T17:58:42Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• Removing Structured Noise with Diffusion Models [14.187153638386379]
  We show that the powerful paradigm of posterior sampling with diffusion models can be extended to include rich, structured, noise models. We demonstrate strong performance gains across various inverse problems with structured noise, outperforming competitive baselines. This opens up new opportunities and relevant practical applications of diffusion modeling for inverse problems in the context of non-Gaussian measurement models.
  arXiv  Detail & Related papers  (2023-01-20T23:42:25Z)
• From Denoising Diffusions to Denoising Markov Models [38.33676858989955]
  Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. We propose a unifying framework generalising this approach to a wide class of spaces and leading to an original extension of score matching.
  arXiv  Detail & Related papers  (2022-11-07T14:34:27Z)
• Discrete Variational Attention Models for Language Generation [51.88612022940496]
  We propose a discrete variational attention model with categorical distribution over the attention mechanism owing to the discrete nature in languages. Thanks to the property of discreteness, the training of our proposed approach does not suffer from posterior collapse.
  arXiv  Detail & Related papers  (2020-04-21T05:49:04Z)

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.