Picture for Hsin-Te Hwang

Hsin-Te Hwang

Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion

Add code
Feb 07, 2020
Figure 1 for Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
Figure 2 for Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
Figure 3 for Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
Figure 4 for Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
Viaarxiv icon

Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion

Add code
Nov 27, 2018
Figure 1 for Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
Figure 2 for Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
Figure 3 for Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
Figure 4 for Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
Viaarxiv icon

Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders

Add code
Aug 29, 2018
Figure 1 for Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
Figure 2 for Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
Figure 3 for Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
Figure 4 for Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
Viaarxiv icon

Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM

Add code
Aug 17, 2018
Figure 1 for Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
Figure 2 for Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
Figure 3 for Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
Figure 4 for Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
Viaarxiv icon

Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks

Add code
Jun 08, 2017
Figure 1 for Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
Figure 2 for Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
Figure 3 for Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
Figure 4 for Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
Viaarxiv icon

Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder

Add code
Oct 13, 2016
Figure 1 for Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
Figure 2 for Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
Figure 3 for Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
Viaarxiv icon

Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network

Add code
Oct 13, 2016
Figure 1 for Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network
Figure 2 for Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network
Figure 3 for Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network
Figure 4 for Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network
Viaarxiv icon