Noise-based audio-visual fusion for robust speech recognition.
Eric K. PattersonSabri GurbuzZekeriya TufekciJohn N. GowdyPublished in: AVSP (2001)
Keyphrases
- speech recognition
- noisy environments
- audio visual
- audio visual speech recognition
- speaker verification
- digit recognition
- person authentication
- multi stream
- multi modal
- multimodal fusion
- hidden markov models
- speech signal
- automatic speech recognition
- language model
- visual information
- noise reduction
- speech enhancement
- background noise
- speaker identification
- speech synthesis
- multimedia
- pattern recognition
- signal to noise ratio
- probabilistic model
- visual data
- speech recognition systems
- emotion recognition
- speech recognizer
- computer vision
- data mining
- audio features
- image data