Use of prosodic information to integrate acoustic and linguistic knowledge in continuous Mandarin speech recognition with very large vocabulary.
Hung-Yun HsiehRen-Yuan LyuLin-Shan LeePublished in: ICSLP (1996)
Keyphrases
- speech recognition
- speaker independent
- speech recognition systems
- hidden markov models
- speech synthesis
- speech recognizer
- speech recognizers
- pattern recognition
- language model
- prosodic features
- noisy environments
- linguistic knowledge
- isolated word
- speaker identification
- automatic speech recognition
- speech signal
- semantic information
- machine learning
- neural network