Validação de corpus para reconhecimento de fala contínua em Português Brasileiro.
Fabiano Weimar dos SantosDante Augusto Couto BaroneAndré Gustavo AdamiPublished in: WebMedia (Companion) (2008)
Keyphrases
- expectation maximization
- em algorithm
- maximum likelihood
- probabilistic model
- generative model
- mixture model
- spanish language
- text corpora
- expectation maximisation
- open domain
- supervised machine learning
- training corpus
- statistical machine translation
- sentence level
- manually annotated
- web pages
- gaussian mixture model
- hidden markov models