Picture for Yen-Ju Lu

Yen-Ju Lu

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Add code
Jul 19, 2022
Figure 1 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 2 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 3 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Figure 4 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
Viaarxiv icon

Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge

Feb 24, 2022
Figure 1 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 2 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 3 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Figure 4 for Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
Viaarxiv icon

Conditional Diffusion Probabilistic Model for Speech Enhancement

Add code
Feb 10, 2022
Figure 1 for Conditional Diffusion Probabilistic Model for Speech Enhancement
Figure 2 for Conditional Diffusion Probabilistic Model for Speech Enhancement
Figure 3 for Conditional Diffusion Probabilistic Model for Speech Enhancement
Figure 4 for Conditional Diffusion Probabilistic Model for Speech Enhancement
Viaarxiv icon

Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem

Add code
Jan 09, 2022
Figure 1 for Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem
Figure 2 for Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem
Figure 3 for Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem
Figure 4 for Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem
Viaarxiv icon

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition

Oct 09, 2021
Figure 1 for An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition
Figure 2 for An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition
Figure 3 for An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition
Figure 4 for An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition
Viaarxiv icon

A Study on Speech Enhancement Based on Diffusion Probabilistic Model

Add code
Jul 25, 2021
Figure 1 for A Study on Speech Enhancement Based on Diffusion Probabilistic Model
Figure 2 for A Study on Speech Enhancement Based on Diffusion Probabilistic Model
Figure 3 for A Study on Speech Enhancement Based on Diffusion Probabilistic Model
Figure 4 for A Study on Speech Enhancement Based on Diffusion Probabilistic Model
Viaarxiv icon

Speech enhancement guided by contextual articulatory information

Nov 15, 2020
Figure 1 for Speech enhancement guided by contextual articulatory information
Figure 2 for Speech enhancement guided by contextual articulatory information
Figure 3 for Speech enhancement guided by contextual articulatory information
Viaarxiv icon

Incorporating Broad Phonetic Information for Speech Enhancement

Aug 13, 2020
Figure 1 for Incorporating Broad Phonetic Information for Speech Enhancement
Figure 2 for Incorporating Broad Phonetic Information for Speech Enhancement
Figure 3 for Incorporating Broad Phonetic Information for Speech Enhancement
Figure 4 for Incorporating Broad Phonetic Information for Speech Enhancement
Viaarxiv icon

Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing

Jun 18, 2020
Figure 1 for Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing
Figure 2 for Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing
Figure 3 for Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing
Figure 4 for Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing
Viaarxiv icon

A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features

Jun 07, 2015
Figure 1 for A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
Figure 2 for A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
Figure 3 for A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
Figure 4 for A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
Viaarxiv icon