Video Augmentation for Improving Audio Speech Recognition under Noise.
Samuel PachoudShaogang GongAndrea CavallaroPublished in: BMVC (2008)
Keyphrases
- speech recognition
- noisy environments
- speaker identification
- speech processing
- multimedia
- speech recognition technology
- automatic speech recognition
- broadcast news
- speech signal
- hidden markov models
- audio signals
- noisy speech
- speech recognizer
- audio visual speech recognition
- visual data
- language model
- video sequences
- speech synthesis
- pattern recognition
- video streams
- video data
- visual speech
- audio signal
- digital video library
- video content
- cepstral coefficients
- speech recognition systems
- background noise
- video frames
- multimedia information
- neural network
- noise model
- audio visual
- signal to noise ratio
- speaker recognition
- video clips
- mel frequency cepstral coefficients
- audio features
- video database
- speaker verification
- word recognition
- speech recognizers
- visual information
- multimedia systems