Deep hybrid architectures and DenseNet35 in speaker-dependent visual speech recognition.
Preethi Jayappa SeegehalliB. Niranjana KrupaPublished in: Signal Image Video Process. (2024)
Keyphrases
- visual speech recognition
- speaker dependent
- speaker identification
- speech recognition
- lip reading
- speaker independent
- hidden markov models
- gaussian mixture model
- speech signal
- visual speech
- noisy environments
- broadcast news
- dynamic textures
- machine learning
- pattern recognition
- feature extraction
- multi modal
- language model
- information retrieval