Minimum classification error training in example based speech and pattern recognition using sparse weight matrices.
Mike MattonDirk Van CompernolleRonald CoolsPublished in: J. Comput. Appl. Math. (2010)
Keyphrases
- minimum classification error
- weight matrices
- discriminative training
- statistical pattern recognition
- classification error
- maximum likelihood estimation
- speech recognition
- hidden markov models
- automatic speech recognition
- weight matrix
- supervised learning
- training examples
- high dimensional
- training samples
- maximum likelihood
- gaussian mixture
- speech signal
- language model
- information extraction
- knn