Inclusion of temporal information into features for speech recognition.
Ben MilnerPublished in: ICSLP (1996)
Keyphrases
- temporal information
- speech recognition
- spatial information
- speech recognition systems
- temporal reasoning
- hidden markov models
- language model
- video sequences
- noisy environments
- speech processing
- speech recognizer
- speech recognition technology
- pattern recognition
- speech signal
- speech synthesis
- temporal sequences
- cepstral coefficients
- speaker identification
- video database
- contextual information
- automatic speech recognition
- co occurrence
- temporal expressions
- temporal dimension
- video clips
- neural network
- natural language processing
- low level
- feature vectors
- image sequences
- high level
- machine learning