A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation

• URL: http://arxiv.org/abs/2405.13762v1
• Date: Wed, 22 May 2024 15:47:14 GMT
• Title: A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
• Authors: Gwanghyun Kim, Alonso Martinez, Yu-Chuan Su, Brendan Jou, José Lezama, Agrim Gupta, Lijun Yu, Lu Jiang, Aren Jansen, Jacob Walker, Krishna Somandepalli,
• Abstract summary: Training diffusion models for audiovisual sequences allows for a range of generation tasks. We propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.
• Score: 32.648815593259485
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variable diffusion timesteps across the temporal dimension and across modalities of the inputs. This formulation offers flexibility to introduce variable noise levels for various portions of the input, hence the term mixture of noise levels. We propose a transformer-based audiovisual latent diffusion model and show that it can be trained in a task-agnostic fashion using our approach to enable a variety of audiovisual generation tasks at inference time. Experiments demonstrate the versatility of our method in tackling cross-modal and multimodal interpolation tasks in the audiovisual space. Notably, our proposed approach surpasses baselines in generating temporally and perceptually consistent samples conditioned on the input. Project page: avdit2024.github.io

Related papers

• Diffusion-based Unsupervised Audio-visual Speech Enhancement [26.937216751657697]
  This paper proposes a new unsupervised audiovisual speech enhancement (AVSE) approach. It combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervisedgenerative AVSE method.
  arXiv  Detail & Related papers  (2024-10-04T12:22:54Z)
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion [61.03681839276652]
  Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
  arXiv  Detail & Related papers  (2024-07-01T15:43:25Z)
• Blue noise for diffusion models [50.99852321110366]
  We introduce a novel and general class of diffusion models taking correlated noise within and across images into account. Our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method.
  arXiv  Detail & Related papers  (2024-02-07T14:59:25Z)
• Training-Free Semantic Video Composition via Pre-trained Diffusion Model [96.0168609879295]
  Current approaches, predominantly trained on videos with adjusted foreground color and lighting, struggle to address deep semantic disparities beyond superficial adjustments. We propose a training-free pipeline employing a pre-trained diffusion model imbued with semantic prior knowledge. Experimental results reveal that our pipeline successfully ensures the visual harmony and inter-frame coherence of the outputs.
  arXiv  Detail & Related papers  (2024-01-17T13:07:22Z)
• DiffSED: Sound Event Detection with Denoising Diffusion [70.18051526555512]
  We reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions.
  arXiv  Detail & Related papers  (2023-08-14T17:29:41Z)
• UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model [1.0874597293913013]
  UnDiff is a diffusion probabilistic model capable of solving various speech inverse tasks. It can be adapted to different tasks including inversion degradation, neural vocoding, and source separation.
  arXiv  Detail & Related papers  (2023-06-01T14:22:55Z)
• A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI [64.71397830291838]
  Generative AI has demonstrated impressive performance in various fields, among which speech synthesis is an interesting direction. With the diffusion model as the most popular generative model, numerous works have attempted two active tasks: text to speech and speech enhancement. This work conducts a survey on audio diffusion model, which is complementary to existing surveys.
  arXiv  Detail & Related papers  (2023-03-23T15:17:15Z)
• Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation [41.292644854306594]
  We propose a novel diffusion-based framework, named Diffusion Co-Speech Gesture (DiffGesture) DiffGesture achieves state-of-theart performance, which renders coherent gestures with better mode coverage and stronger audio correlations.
  arXiv  Detail & Related papers  (2023-03-16T07:32:31Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)

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.