Projects

Kazakh language Text-to-Speech technology

Instructions for Kazakh TTS demo:

– Insert the Kazakh text inside the box below (Please use only Cyrillic alphabetic characters and punctuation marks, i.e. numbers and other special symbols should be written in textual forms. For better performance, split the long text into shorter segments.)
– Then click the “GET AUDIO” button
– The page will reload and you will find the Audio of your text under the box. Then press the Play button to listen to the Audio

In order to stimulate research and innovation and also encourage the use of Kazakh in the digital sphere, the Institute of smart systems and artificial intelligence (ISSAI) of Nazarbayev University conducted a Kazakh language speech synthesis project. Text-to-speech (TTS) conversion is the artificial production of human speech. It allows to convert the written text to the speech signal. TTS is an essential  component in many applications such as interactive smart assistant systems,  navigation systems, announcement systems and assistive technologies for the visually-impaired. It enables human-technology interaction without requiring visual and tactile interfaces.

To build Kazakh TTS systems, we used the KazakhTTS database developed by ISSAI. KazakhTTS is a high-quality open-source speech database which contains over 90 hours of audio recorded by two professional speakers (one male and one female). The database is publicly available for both academic and commercial use upon request under Creative Commons Attribution 4.0 International License.

If you use the ISSAI’s KazakhTTS database for commercial purposes, please add this statement to your product or service:

Our product uses ISSAI KazakhTTS (https://doi.org/10.48342/bkzq-tp58), which is available under a Creative Commons Attribution 4.0 International License.

If you use the ISSAI’s KazakhTTS database for research, please cite it as:

Mussakhojayeva, S., Janaliyeva, A., Mirzakhmetov, A., Khassanov, Y. and Varol, H.A., 2021. KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset. arXiv preprint arXiv:2104.08459

Watch the video of the Qorqyt ata story narrated by the male synthetic voice called Iseke
Watch the video of the Dina Nurpeisova story narrated by the female synthetic voice called Raya
GitHub icon
Powered by GitHub