Improved Features and Models for Detecting Edit Disfluencies in Transcribing Spontaneous Mandarin Speech.
Che-Kuang LinLin-Shan LeePublished in: IEEE Trans. Speech Audio Process. (2009)
Keyphrases
- classification models
- speech recognition
- feature extraction
- prior knowledge
- machine learning
- predictive power
- abstraction levels
- low level
- probabilistic model
- co occurrence
- feature space
- learned models
- object recognition
- extracted features
- speech signal
- neural network
- linear predictive coding
- machine learning approaches
- complex systems
- human computer interaction
- feature set