Keyphrases
- speech signal
- speaker identification
- audio visual
- audio stream
- linear prediction
- broadcast news
- linear predictive
- linear predictive coding
- speech recognition
- mel frequency cepstral coefficients
- audio signals
- acoustic features
- cepstral features
- emotion recognition
- automatic speech recognition
- cepstral coefficients
- text to speech
- coding scheme
- audio features
- speech quality
- digital audio
- speech processing
- audio recordings
- speech music discrimination
- speaker recognition
- noisy environments
- multimedia
- hidden markov models
- voice activity detection
- signal processing
- multi modal
- video signals
- automatic transcription
- spoken documents
- visual speech
- coding method
- audio signal
- acoustic signals
- audio video
- visual information
- image quality
- speech synthesis
- multi stream
- spoken language
- non stationary
- signal to noise ratio
- human language
- spoken document retrieval
- language model
- multimodal interfaces