Advanced speech synthesizer technology that uses deep neural networks to create natural-sounding computer voices for the use and accessibility of visually impaired people.
Neural SpeechLab integrates natural-sounding computer voices created with the most advanced modern technologies using deep neural networks. The software’s specialized functionalities are targeted at helping people with visual impairments.
Neural SpeechLab converts text entered into a computer into speech. With it a user can read, create, and process Bulgarian language texts in word processing programs or the Internet in combination with screen readers such as Jaws, NVDA, and TalkBack among others. Through the selection and combination of various fine settings and features, the program allows a visually impaired user to tailor how she reads to her specific needs.
The software product was implemented by the Institute of Information and Communication Technologies at the BAS (Bulgarian Academy of Science), and Astea Solutions created its integration with Android and Windows devices.
