Robust Audio-Visual Mandarin Speech Recognition Based On Adaptive Decision Fusion And Tone Features.
Hong LiuZhengyan ChenWei ShiPublished in: ICIP (2020)
Keyphrases
- speech recognition
- audio visual
- audio visual speech recognition
- decision fusion
- noisy environments
- speech recognition systems
- hidden markov models
- multi modal
- automatic speech recognition
- speech signal
- audio features
- pattern recognition
- speaker independent
- language model
- speech synthesis
- speech recognizer
- feature vectors
- emotion recognition
- speaker identification
- speaker verification
- multi stream
- feature extraction
- visual information
- digit recognition
- feature space
- audio signal
- multimedia
- image retrieval
- low level
- image features