The MDG group of companies, part of the Sberbank ecosystem, announced the development of an advanced speech synthesis platform, which is said to ensure smooth and expressive reading of any text.
The presented solution is the third generation of the speech synthesis system. High-quality audio signals are generated by complex neural network models. The developers claim that the result of these algorithms is the most realistic synthesis of Russian-language speech.
The platform includes a module for predicting stress in words that are not yet in the base dictionary. In addition, automatic correction of common spelling errors is provided. Thanks to deep linguistic analysis of the text, pronunciation will correspond to the norms of the language even in difficult cases.
Another advantage of the platform is that it does not require expensive servers equipped with GPU accelerators. You can use the technology in two ways: through a cloud service or by integrating it into your own solution.
Among the possible areas of application of the development are chatbots and voice assistants, information and notification services, voice services with instant synthesis of any text during a call, etc.
βIn automated scenarios of communication with clients, the technology allows you to interact individually with each subscriber, since there are no fixed messages, and any text can be synthesized during the call,β say the developers.
You can try the technology .
Source: 3dnews.ru