Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
This work addresses the problem of improving communication accessibility for people with hearing impairment, but it is incremental as it builds on existing methods and datasets.
The paper tackles automatic recognition of Cued Speech, a visual communication tool for hearing-impaired individuals, by proposing a system using pre-trained visual feature extraction and multistream neural networks, achieving a phonetic decoding accuracy of 70.88%.
This paper proposes a simple and effective approach for automatic recognition of Cued Speech (CS), a visual communication tool that helps people with hearing impairment to understand spoken language with the help of hand gestures that can uniquely identify the uttered phonemes in complement to lipreading. The proposed approach is based on a pre-trained hand and lips tracker used for visual feature extraction and a phonetic decoder based on a multistream recurrent neural network trained with connectionist temporal classification loss and combined with a pronunciation lexicon. The proposed system is evaluated on an updated version of the French CS dataset CSF18 for which the phonetic transcription has been manually checked and corrected. With a decoding accuracy at the phonetic level of 70.88%, the proposed system outperforms our previous CNN-HMM decoder and competes with more complex baselines.