Combining Residual Networks with LSTMs for Lipreading

We propose an end-to-end deep learning architecture for word-level visual speech recognition. The system is a combination of spatiotemporal convolution, residual and bidirectional Long-Short Term Memory networks. We trained and evaluated it on the Lipreading In-The-Wild benchmark, a challenging database of 500-size vocabulary consisting of video excerpts from BBC TV broadcasts. The proposed network attains word accuracy equal to 83.0%, yielding 6.8% absolute improvement over the current state-of-the-art.