Mispronunciation Detection Leveraging Maximum Performance Criterion Training of Acoustic Models and Decision Functions.
Yao-Chi HsuMing-Han YangHsiao-Tsung HungBerlin ChenPublished in: INTERSPEECH (2016)
Keyphrases
- decision functions
- acoustic models
- speech recognition
- decision rules
- training process
- training examples
- decision function
- hidden markov models
- automatic speech recognition
- training set
- broadcast news
- rough sets
- training samples
- machine learning
- supervised learning
- support vector machine
- knn
- support vectors
- feature space