Improving speech recognition accuracy with multi-confidence thresholding.
Shuangyu ChangPublished in: INTERSPEECH (2006)
Keyphrases
- recognition accuracy
- recognition rate
- face recognition
- improve the recognition rate
- speech recognition
- gray level
- audio visual
- face databases
- edge detection
- denoising
- image segmentation
- post processing
- speech signal
- confidence measure
- confidence level
- thresholding method
- speech synthesis
- wavelet transform
- image processing
- emotion recognition
- text to speech
- recognition engine
- elastic graph matching
- endpoint detection