There are some demos that preformed on ESD database from previous publications, those are:
[1] Seq2Seq-EVC Github[2] CycleGAN-EVC Github[3] StarGAN-EVC Github[4] VAWGAN-EVC Github
May 2021 - Add emotional text-to-speech speech samples into our website!
May 2021 - Add speech samples from Seq2Seq-EVC into our website!
Feb 2021 - Add speech samples from StarGAN-EVC into our website!
Jan 2021 - Add speech samples from VAWGAN-EVC and CycleGAN-EVC into our website!
Invitation
"It is not the end. It is the beginning."
— Stephenie Meyer
We will be continuing to update and include more speech samples into this website as long as our research on "emotional voice conversion" is going on. If you are doing emotional voice conversion with our ESD database, you are welcome to put your speech samples on this website. Please feel free to contact me with: zhoukun@u.nus.edu
Reference
[1] Seq2seq-EVC:
Kun Zhou, Berrak Sisman, and Haizhou Li, "Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training", Submitted to Interspeech 2021, 2021
[2] CycleGAN-EVC:
Kun Zhou, Berrak Sisman, and Haizhou Li, "Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data", Proc. odyssey 2020 the speaker and language recognition workshop, 2020, pp. 230–237.
[3] StarGAN-EVC:
Rizos, Georgios, Alice Baird, Max Elliott, and Björn Schuller, "Stargan for Emotional Speech Conversion: Validated by Data Augmentation of End-To-End Emotion Recognition." In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.
[4] VAWGAN-EVC:
Kun Zhou, Berrak Sisman, and Haizhou Li, "VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech", In IEEE Spoken Language Workshop (SLT), 2021