Speaker Verification Based on Synchronous Speech and Video Features.
Hiroto NakajimaShinichi KawamotoPublished in: GCCE (2023)
Keyphrases
- speaker verification
- prosodic features
- speaker recognition
- noisy environments
- feature vectors
- key frames
- speech recognition
- extracting features
- low level
- mel frequency cepstral coefficients
- high dimensional
- acoustic features
- video content
- audio features
- audio visual
- speech synthesis
- neural network
- multimedia
- video data
- image features
- emotion recognition
- artificial neural networks
- visual speech
- feature space