Feature Fusion Based Audio-Visual Speaker Identification Using Hidden Markov Model under Different Lighting Variations.
Md. Rabiul IslamMd. Abdus SobhanPublished in: Appl. Comput. Intell. Soft Comput. (2014)
Keyphrases
- audio visual
- hidden markov models
- speaker identification
- speech recognition
- audio features
- speech signal
- multi modal
- visual information
- multi stream
- visual data
- gaussian mixture model
- noisy environments
- feature extraction
- multimedia
- automatic speech recognition
- broadcast news
- computer vision
- eye movements
- three dimensional
- data sets