Discriminative training of n-gram language models for speech recognition via linear programming.
Vladimir MagdinHui JiangPublished in: ASRU (2009)
Keyphrases
- discriminative training
- speech recognition
- linear programming
- automatic speech recognition
- hidden markov models
- acoustic models
- n gram
- language model
- speech signal
- noisy environments
- maximum likelihood
- pattern recognition
- speech synthesis
- speech recognizer
- speech recognition technology
- probabilistic interpretation
- language independent
- speech recognition systems
- speaker independent
- speaker identification
- broadcast news
- posterior probability
- supervised learning
- support vector machine
- probabilistic model
- machine learning
- data mining