Unsupervised Composable Representations for Audio

• URL: http://arxiv.org/abs/2408.09792v1
• Date: Mon, 19 Aug 2024 08:41:09 GMT
• Title: Unsupervised Composable Representations for Audio
• Authors: Giovanni Bindi, Philippe Esling,
• Abstract summary: Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning. In this paper, we focus on the problem of compositional representation learning for music data, specifically targeting the fully-unsupervised setting. We propose a framework that leverages an explicit compositional inductive bias, defined by a flexible auto-encoding objective.
• Score: 0.9888599167642799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we focus on the problem of compositional representation learning for music data, specifically targeting the fully-unsupervised setting. We propose a simple and extensible framework that leverages an explicit compositional inductive bias, defined by a flexible auto-encoding objective that can leverage any of the current state-of-art generative models. We demonstrate that our framework, used with diffusion models, naturally addresses the task of unsupervised audio source separation, showing that our model is able to perform high-quality separation. Our findings reveal that our proposal achieves comparable or superior performance with respect to other blind source separation methods and, furthermore, it even surpasses current state-of-art supervised baselines on signal-to-interference ratio metrics. Additionally, by learning an a-posteriori masking diffusion model in the space of composable representations, we achieve a system capable of seamlessly performing unsupervised source separation, unconditional generation, and variation generation. Finally, as our proposal works in the latent space of pre-trained neural audio codecs, it also provides a lower computational cost with respect to other neural baselines.

Related papers

• Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling [25.705179111920806]
  This work addresses the question of why and when diffusion models excel at learning high-quality representations in a self-supervised manner. We develop a mathematical framework based on a low-dimensional data model and posterior estimation, revealing a fundamental trade-off between generation and representation quality near the final stage of image generation. Building on these insights, we propose an ensemble method that aggregates features across noise levels, significantly improving both clean performance and robustness under label noise.
  arXiv  Detail & Related papers  (2025-02-09T01:58:28Z)
• Nested Diffusion Models Using Hierarchical Latent Priors [23.605302440082994]
  We introduce nested diffusion models, an efficient and powerful hierarchical generative framework. Our approach employs a series of diffusion models to progressively generate latent variables at different semantic levels. To construct these latent variables, we leverage a pre-trained visual encoder, which learns strong semantic visual representations.
  arXiv  Detail & Related papers  (2024-12-08T16:13:39Z)
• MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion [14.907473847787541]
  We propose Masked Diffusion Conditional (MacDiff) as a unified framework for human skeleton modeling. For the first time, we leverage diffusion models as effective skeleton representation learners. MacDiff achieves state-of-the-art performance on representation learning benchmarks while maintaining the competence for generative tasks.
  arXiv  Detail & Related papers  (2024-09-16T17:06:10Z)
• Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling [39.80957479349776]
  We investigate the prosody modeling capabilities of the discrete space of an RVQ-VAE model, modifying it to operate on the phoneme-level. We show that the phoneme-level discrete latent representations achieves a high degree of disentanglement, capturing fine-grained prosodic information that is robust and transferable.
  arXiv  Detail & Related papers  (2024-09-13T09:27:05Z)
• SODA: Bottleneck Diffusion Models for Representation Learning [75.7331354734152]
  We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, which distills a source view into a compact representation, that guides the generation of related novel views. We show that by imposing a tight bottleneck between the encoder and a denoising decoder, we can turn diffusion models into strong representation learners.
  arXiv  Detail & Related papers  (2023-11-29T18:53:34Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Structure-Regularized Attention for Deformable Object Representation [17.120035855774344]
  Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by enabling unconstrained pairwise interactions between elements. We consider learning representations for deformable objects which can benefit from context exploitation by modeling the structural dependencies that the data intrinsically possesses.
  arXiv  Detail & Related papers  (2021-06-12T03:10:17Z)
• Cross-Modal Discrete Representation Learning [73.68393416984618]
  We present a self-supervised learning framework that learns a representation that captures finer levels of granularity across different modalities. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities.
  arXiv  Detail & Related papers  (2021-06-10T00:23:33Z)
• Counterfactual Generative Networks [59.080843365828756]
  We propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background. We show that the counterfactual images can improve out-of-distribution with a marginal drop in performance on the original classification task.
  arXiv  Detail & Related papers  (2021-01-15T10:23:12Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)
• High-Fidelity Synthesis with Disentangled Representation [60.19657080953252]
  We propose an Information-Distillation Generative Adrial Network (ID-GAN) for disentanglement learning and high-fidelity synthesis. Our method learns disentangled representation using VAE-based models, and distills the learned representation with an additional nuisance variable to the separate GAN-based generator for high-fidelity synthesis. Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation.
  arXiv  Detail & Related papers  (2020-01-13T14:39:40Z)

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.