Artificial neural network technology for lips reading

The paper presents the use of neural networks for the task of automated speech reading by lips articulation. Speech recognition is performed in two stages. First, a face search is performed and the lips area is selected in a separate frame of the video sequence using Haar features. Then the sequence of frames goes to the input of deep learning convolutional and recurrent neural networks for speech viseme recognition. Experimental studies were carried out using independently obtained videos with Russian-speaking speakers.

Abstract licence: CC BY

6 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.