Improving Mandarin Tone Recognition Based on DNN by Combining Acoustic and Articulatory Features Using Extended Recognition Networks.
Ju LinWei LiYingming GaoYanlu XieNancy F. ChenSabato Marco SiniscalchiJinsong ZhangChin-Hui LeePublished in: J. Signal Process. Syst. (2018)
Keyphrases
- recognition rate
- feature extraction
- recognition accuracy
- object recognition
- robust recognition
- recognition algorithm
- pattern recognition
- feature extractor
- object class recognition
- automatic recognition
- speech recognition systems
- recognition process
- action recognition
- social networks
- extracting features
- handwritten characters
- discrimination power
- image features
- classification accuracy
- occluded objects
- object models
- human computer interaction
- method for face recognition
- low level
- invariant moments
- feature vectors