Improving speech recognition accuracy with contextual phonemes and MMI training.
Anne-Marie DerouaultBernard MérialdoPublished in: ICASSP (1989)
Keyphrases
- recognition accuracy
- speech recognition
- speech signal
- automatic speech recognition
- speech synthesis
- recognition rate
- face recognition
- text to speech
- hearing impaired
- training process
- contextual information
- hidden markov models
- language model
- speech recognition systems
- training examples
- improve the recognition rate
- audio visual
- training samples
- speech corpus
- elastic graph matching
- speech recognizer
- discriminating power
- context sensitive
- speaker identification
- supervised learning
- multi class
- acoustic features
- broadcast news
- spoken language
- principal component analysis
- object detection
- pattern recognition
- neural network