Robust end-to-end deep audiovisual speech recognition
This work addresses the problem of robust speech recognition for applications in noisy environments, though it is incremental as it builds on existing RNN and CTC techniques.
The paper tackles the challenge of multi-modal speech recognition by developing an end-to-end audiovisual speech recognizer using RNNs with CTC loss, achieving improved phone accuracy on the IBM ViaVoice database in both clean and noisy conditions compared to prior methods.
Speech is one of the most effective ways of communication among humans. Even though audio is the most common way of transmitting speech, very important information can be found in other modalities, such as vision. Vision is particularly useful when the acoustic signal is corrupted. Multi-modal speech recognition however has not yet found wide-spread use, mostly because the temporal alignment and fusion of the different information sources is challenging. This paper presents an end-to-end audiovisual speech recognizer (AVSR), based on recurrent neural networks (RNN) with a connectionist temporal classification (CTC) loss function. CTC creates sparse "peaky" output activations, and we analyze the differences in the alignments of output targets (phonemes or visemes) between audio-only, video-only, and audio-visual feature representations. We present the first such experiments on the large vocabulary IBM ViaVoice database, which outperform previously published approaches on phone accuracy in clean and noisy conditions.