Nagoya, Japan

Wen-Chin Huang (unilight)

Expert
@unilight

Assistant professor at Nagoya University, Japan.

unilight.github.io/

sheet. Speech Human Evaluation Estimation Toolkit (SHEET)

138

seq2seq-vc. A sequence-to-sequence voice conversion toolkit.

113

s3prl-vc. S3PRL-VC: A Voice Conversion Toolkit based on S3PRL

101

R-NET-in-Tensorflow. R-NET implementation in TensorFlow.

77

LDNet. Official implementation of the paper: "LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech"

68

cdvae-vc. TensorFlow Implementation of CDVAE-VC.

54

jatts. JATTS: A modern, research-oriented Japanese Text-to-speech Open-sourced Toolkit

43

LibriTTS-R-MFA.

5

Generative-Compression. Tensorflow implementation of paper Generative Compression.

4

VAE-WNV-VC-Demo. Demo page for VAE adapted WaveNet Vocoder VC

2

ImageQA_LAB. An LSTM neural network used to proceed image QA, implemented with Tensorflow.

1

is2023-accent-subjective-test. JavaScript

1

Publication-Demos. HTML

1

CDVAE-Demo. Demo page for CDVAE.

1

spectrogram-visualizer. A spectrogram visualizer implemented using pyqt.

1

CDVAE-GAN-CLS-Demo. Demo page for CDVAE extended with GAN and adversarial classifier (CLS)

1

CoinChoreoApp. A JavaFX application to help choreographers

1

codec-tts-mos. Python

1
18
Apply