Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition.
Vlasios DoumpiotisWilliam ByrnePublished in: Speech Commun. (2006)
Keyphrases
- bayes risk
- discriminative training
- posterior probability
- automatic speech recognition
- loss function
- probabilistic interpretation
- hidden markov models
- upper and lower bounds
- maximum likelihood
- image segmentation
- bayesian framework
- generative model
- machine learning
- probabilistic model
- semi supervised
- semi supervised learning
- co training
- vector quantizer
- feature vectors
- high dimensional