Improved Minimum Phone Error based Discriminative Training of Acoustic Models for Mandarin Large Vocabulary Continuous Speech Recognition.
Shih-Hung LiuFang-Hui ChuYueng-Tien LoBerlin ChenPublished in: Int. J. Comput. Linguistics Chin. Lang. Process. (2008)
Keyphrases
- acoustic models
- speech recognition
- discriminative training
- speech recognizer
- automatic speech recognition
- broadcast news
- speaker independent
- hidden markov models
- maximum likelihood
- spoken language
- speech signal
- probabilistic interpretation
- language model
- pattern recognition
- support vector machine
- speech recognition systems
- noisy environments
- posterior probability
- speaker identification
- neural network
- random variables
- support vector
- training data