Rct: Random Consistency Training for Semi-supervised Sound Event Detection (2021-10-21T00:00:00.000000Z)

TL;DR

A random consistency training (RCT) strategy is proposed to fuse with the teacher-student model to stabilize the training, and a hard mixup data augmentation is proposed to account for the additive property of sounds.

Abstract

Sound event detection (SED), as a core module of acoustic environmental analysis, suffers from the problem of data deficiency. The integration of semi-supervised learning (SSL) largely mitigates such problem while bringing no extra annotation budget. This paper researches on several core modules of SSL, and introduces a random consistency training (RCT) strategy. First, a self-consistency loss is proposed to fuse with the teacher-student model to stabilize the training. Second, a hard mixup data augmentation is proposed to account for the additive property of sounds. Third, a random augmentation scheme is applied to flexibly combine different types of data augmentations. Experiments show that the proposed strategy outperform other widely-used strategies.

Authors

Nian Shao

3 papers

Xiaofei Li

3 papers

Erfan Loweimi

2 papers

TL;DR

Abstract

Authors

References33 items

Heavily Augmented Sound Event Detection utilizing Weak Predictions

Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4

Sound Event Detection by Consistency Training and Pseudo-Labeling With Feature-Pyramid Convolutional Recurrent Neural Networks

Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection

Randaugment: Practical automated data augmentation with a reduced search space

A survey on Image Data Augmentation for Deep Learning

Sound Event Detection in Domestic Environments with Weakly Labeled Data and Soundscape Synthesis

AutoAugment: Learning Augmentation Strategies From Data

Unsupervised Data Augmentation for Consistency Training

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Interpolation Consistency Training for Semi-Supervised Learning

Forward Noise Adjustment Scheme for Data Augmentation

Learning from Between-class Examples for Deep Sound Recognition

mixup: Beyond Empirical Risk Minimization

Computational Analysis of Sound Scenes and Events

Learnable pooling with Context Gating for video classification

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

Temporal Ensembling for Semi-Supervised Learning

Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning

Metrics for Polyphonic Sound Event Detection

Detection and Classification of Acoustic Scenes and Events

Adam: A Method for Stochastic Optimization

Learning with Pseudo-Ensembles

ZHENG USTC TEAM’S SUBMISSION FOR DCASE2021 TASK4 - SEMI-SUPERVISED SOUND EVENT DETECTION Technical

IMPROVED PSEUDO-LABELING METHOD FOR SEMI-SUPERVISED SOUND EVENT DETECTION Technical

INTEGRATING ADVANTAGES OF RECURRENT AND TRANSFORMER STRUCTURES FOR SOUND EVENT DETECTION IN MULTIPLE SCENARIOS Technical

SOUND EVENT DETECTION USING METRIC LEARNING AND FOCAL LOSS FOR DCASE 2021 TASK 4 Technical Report

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

SEMI-SUPERVISED SOUND EVENT DETECTION BASED ON MEAN TEACHER WITH POWER POOLING AND DATA AUGMENTATION Technical

MEAN TEACHER WITH DATA AUGMENTATION FOR DCASE 2019 TASK 4

MEAN TEACHER CONVOLUTION SYSTEM FOR DCASE 2018 TASK 4

A Software Framework for Musical Data Augmentation

Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names