Improving non-native mispronunciation detection and enriching diagnostic feedback with DNN-based speech attribute modeling.
Wei LiSabato Marco SiniscalchiNancy F. ChenChin-Hui LeePublished in: ICASSP (2016)
Keyphrases
- speech recognition
- automatic detection
- voice activity detection
- detection accuracy
- detection method
- detection rate
- disease diagnosis
- speech synthesis
- text to speech
- modeling method
- audio visual
- training process
- false alarms
- real time
- object detection
- relevance feedback
- probabilistic model
- pattern recognition
- video sequences
- bayesian networks
- decision making