The St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS) reported that scientists at the institution have trained a neural network to read lips through a smartphone. This should facilitate the use of voice commands in very nosy environments.
«We have developed a smartphone application that recognizes spoken speech and reads the user's words from the lips, analyzing the video signal from the gadget's camera. The program combines and analyzes information from two sources to improve recognition accuracy. Experiments have shown that such a hybrid system recognizes human commands much more effectively in difficult and noisy conditions,» said Denis Ivanko, Senior Researcher at the Laboratory of Speech and Multimodal Interfaces at SPC RAS.
