Speaker-independent-emotional-voice-conversion-based-on-conditional-VAW-GAN-and-CWT

This is the implementation of the Interspeech 2020 paper "Converting anyone's emotion: steps towards speaker-independent emotional voice conversion". Please kindly cite our paper if you are using our codes.

Getting Started

Prerequisites

• Ubuntu 16.04
• Python 3.6
  • Tensorflow-gpu 1.5.0
  • PyWorld
  • librosa
  • soundfile
  • numpy 1.14.0
  • sklearn
  • glob
  • sprocket-vc
  • pycwt
  • scipy

Usage

1. Prepare your dataset.

Please follow the file structure:

training_dir: ./data/wav/training_set/*/*.wav

evaluation_dir ./data/wav/evaluation_set/*/*.wav

For example: "./data/wav/training_set/Angry/0001.wav"

2. Activate your virtual enviroment.

source activate [your env]

3. Train VAW-GAN for prosody.

./train_f0.sh
# Remember to change the source and target dir in "architecture-vawgan-vcc2016.json"

4. Train VAW-GAN for spectrum.

./train_sp.sh
# Remember to change the source and target dir in "architecture-vawgan-vcc2016.json"

5. Generate the converted emotional speech.

./convert.sh

Note: The codes are based on VAW-GAN Voice Conversion: https://github.com/JeremyCCHsu/vae-npvc/tree/vawgan