A distinctive feature based method for evaluating the phonetic transcription of a non-native speech database.
Jinsong ZhangDongning WangWen CaoZiyu XiongPublished in: ISCSLP (2010)
Keyphrases
- database
- detection method
- high accuracy
- data sets
- high precision
- segmentation method
- computational cost
- probabilistic model
- support vector machine
- support vector machine svm
- pattern recognition
- speech recognition
- databases
- preprocessing
- pairwise
- significant improvement
- dynamic programming
- image features
- computational complexity
- error rate
- similarity measure