Estimating speech from lip dynamics
This work addresses the challenge of speech estimation from visual cues for applications in silent communication or assistive technologies, but it is incremental as it builds on existing methods like HMMs and uses a standard dataset.
The researchers tackled the problem of lip reading without audio by developing an algorithm that processes video to extract lip positions, classifies them into visemes and phonemes, and uses Hidden Markov Models to predict spoken words, achieving results on the GRID corpus.
The goal of this project is to develop a limited lip reading algorithm for a subset of the English language. We consider a scenario in which no audio information is available. The raw video is processed and the position of the lips in each frame is extracted. We then prepare the lip data for processing and classify the lips into visemes and phonemes. Hidden Markov Models are used to predict the words the speaker is saying based on the sequences of classified phonemes and visemes. The GRID audiovisual sentence corpus [10][11] database is used for our study.