Kazakh language speech recognition project launched in Kazakhstan
The project was developed by the Institute of Smart Systems and Artificial Intelligence based at Nazarbayev University (ISSAI). The speech synthesis initiative was developed with the aim of developing scientific research and innovation, as well as promoting the use of the Kazakh language in the digital sphere as part of the implementation of the message of the First President N.A. Nazarbayev.
The KazakhTTS database is used to build a Kazakh speech processing system. KazakhTTS is a high-quality, open-access speech database containing over 90 hours of audio recorded by two professional voice actors, a man and a woman. The database is publicly available for academic and commercial use upon request under a Creative Commons Attribution 4.0 international license.
Text-to-speech is the artificial production of human speech. It allows you to process written text into a speech signal. Such technology is an important component of many applications, such as networked virtual assistants, navigation systems, public address systems, assistive technologies for the visually impaired, where Kazakh text is required to be spoken. It enables human interaction with technology without the need for a visual and tactile interface.
To get acquainted with the project, follow the link.