DiffSED: Sound Event Detection with Denoising Diffusion

• URL: http://arxiv.org/abs/2308.07293v2
• Date: Wed, 16 Aug 2023 18:57:28 GMT
• Title: DiffSED: Sound Event Detection with Denoising Diffusion
• Authors: Swapnil Bhosale, Sauradip Nag, Diptesh Kanojia, Jiankang Deng, Xiatian Zhu
• Abstract summary: 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.
• Score: 70.18051526555512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the splitand-classify (i.e., frame-level) strategy or the more principled event-level modeling approach, all existing methods consider the SED problem from the discriminative learning perspective. In this work, 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, conditioned on a target audio sample. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions in the elegant Transformer decoder framework. Doing so enables the model generate accurate event boundaries from even noisy queries during inference. Extensive experiments on the Urban-SED and EPIC-Sounds datasets demonstrate that our model significantly outperforms existing alternatives, with 40+% faster convergence in training.

Related papers

• DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions [52.63323657077447]
  We propose DNMOT, an end-to-end trainable DeNoising Transformer for multiple object tracking. Specifically, we augment the trajectory with noises during training and make our model learn the denoising process in an encoder-decoder architecture. We conduct extensive experiments on the MOT17, MOT20, and DanceTrack datasets, and the experimental results show that our method outperforms previous state-of-the-art methods by a clear margin.
  arXiv  Detail & Related papers  (2023-09-09T04:40:01Z)
• DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection [38.12212015133935]
  A novel framework, DiffusionVMR, is proposed to redefine the two tasks as a unified conditional denoising generation process. Experiments conducted on five widely-used benchmarks demonstrate the effectiveness and flexibility of the proposed DiffusionVMR.
  arXiv  Detail & Related papers  (2023-08-29T08:20:23Z)
• DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion [137.8749239614528]
  We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video.
  arXiv  Detail & Related papers  (2023-03-27T00:40:52Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models [95.97506031821217]
  We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training. The method requires a short (3 seconds) sample from the target person, and generation is steered at inference time, without any training steps.
  arXiv  Detail & Related papers  (2022-06-05T19:45:29Z)
• Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection [12.915110466077866]
  Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level predictions, converting it into a sequence multi-label classification problem. This paper firstly presents the 1D Detection Transformer (1D-DETR), inspired by Detection Transformer. Given the characteristics of SED, the audio query and a one-to-many matching strategy are added to 1D-DETR to form the model of Sound Event Detection Transformer (SEDT)
  arXiv  Detail & Related papers  (2021-10-05T12:56:23Z)
• Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model [26.76830553508229]
  Hypergeometric Learning (HGL) is a denoising algorithm for distantly supervised named entity recognition. HGL takes both noise distribution and instance-level confidence into consideration. Experiments show that HGL can effectively denoise the weakly-labeled data retrieved from distant supervision.
  arXiv  Detail & Related papers  (2021-06-17T04:01:25Z)
• Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures [23.568610919253352]
  This paper proposes a semi-supervised method for generating pseudo-labels from unsupervised data using a student-teacher scheme that balances self-training and cross-training. The results of these methods on both "validation" and "public evaluation" sets of DESED database show significant improvement compared to the state-of-the art systems in semi-supervised learning.
  arXiv  Detail & Related papers  (2021-05-27T18:46:59Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)

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.