Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System.
Marina ZimmermannMostafa Mehdipour-GhaziHazim Kemal EkenelJean-Philippe ThiranPublished in: CoRR (2017)
Keyphrases
- visual speech
- visual speech recognition
- hidden markov models
- speaker identification
- gaussian mixture model
- principal component analysis
- speech recognition
- feature extraction
- speech signal
- feature space
- face images
- expectation maximization
- face recognition
- feature vectors
- background subtraction
- lip reading
- k means
- audio signals
- computational complexity
- mel frequency cepstral coefficients