Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Zheng-Hua Tan

Zheng-Hua Tan

Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Jul 04, 2022
Claus Meyer Larsen, Peter Koch, Zheng-Hua Tan

Figure 1 for Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Figure 2 for Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Figure 3 for Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Figure 4 for Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay

Access Paper or Ask Questions

Complex Recurrent Variational Autoencoder for Speech Enhancement

Apr 05, 2022
Yuying Xie, Thomas Arildsen, Zheng-Hua Tan

Figure 1 for Complex Recurrent Variational Autoencoder for Speech Enhancement

Figure 2 for Complex Recurrent Variational Autoencoder for Speech Enhancement

Figure 3 for Complex Recurrent Variational Autoencoder for Speech Enhancement

Figure 4 for Complex Recurrent Variational Autoencoder for Speech Enhancement

* submitted to INTERSPEECH 2022

Access Paper or Ask Questions

Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective

Apr 05, 2022
Yuying Xie, Thomas Arildsen, Zheng-Hua Tan

Figure 1 for Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective

Figure 2 for Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective

Figure 3 for Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective

Figure 4 for Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective

* Published in: 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)

Access Paper or Ask Questions

On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification

Jan 17, 2022
Achintya kr. Sarkar, Zheng-Hua Tan

Access Paper or Ask Questions

Deep Spoken Keyword Spotting: An Overview

Nov 20, 2021
Iván López-Espejo, Zheng-Hua Tan, John Hansen, Jesper Jensen

Figure 1 for Deep Spoken Keyword Spotting: An Overview

Figure 2 for Deep Spoken Keyword Spotting: An Overview

Figure 3 for Deep Spoken Keyword Spotting: An Overview

Figure 4 for Deep Spoken Keyword Spotting: An Overview

Access Paper or Ask Questions