Neural TTS for Kannada -Indistinguishable from human speech.

State-of-the-art Deep Neural network based TTS engine developed for Kannada

Our TTS system was able to achieve an MOS of 4.42 ± 0.53 when compared to the ground truth 4.55 ± 0.56 based on the evaluation of 25 Kannada natives.

A survey was conducted to compare our synthesized speech with the human speech and it was seen that people preferred the synthesized speech over human speech.

Here are a few audio samples of the synthesized speech developed by RaGaVeRa's Kannada TTS.

01.wav
03.wav
05.wav
06.wav
08.wav
09.wav
10.wav
11.wav

Below is the side by side comparison of human speech with synthesized speech.

Human Speech

Synthesized speech

gtaudio0.wav
saudio_0.wav
gtaudio1.wav
saudio_1.wav
gtaudio2.wav
saudio_2.wav
gtaudio3.wav
saudio_3.wav
gtaudio4.wav
saudio_4.wav

Below is a link to a survey where you can listen to some more audio samples and rate them accordingly.

We at RaGaVeRa will be further researching and developing TTS for multiple Indian language in multiple voices.