Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding
This work addresses communication challenges for deaf or hard-of-hearing individuals by providing an incremental analysis of modality interactions in a specific domain.
The study tackled the problem of understanding hand-lip dynamics in French Cued Speech for deaf communication by training a neural network with attention mechanisms and CTC decoding on a new dataset, achieving a benchmark for word-level recognition.
Hard of hearing or profoundly deaf people make use of cued speech (CS) as a communication tool to understand spoken language. By delivering cues that are relevant to the phonetic information, CS offers a way to enhance lipreading. In literature, there have been several studies on the dynamics between the hand and the lips in the context of human production. This article proposes a way to investigate how a neural network learns this relation for a single speaker while performing a recognition task using attention mechanisms. Further, an analysis of the learnt dynamics is utilized to establish the relationship between the two modalities and extract automatic segments. For the purpose of this study, a new dataset has been recorded for French CS. Along with the release of this dataset, a benchmark will be reported for word-level recognition, a novelty in the automatic recognition of French CS.