Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition.
Mengzhe GengShansong LiuJianwei YuXurong XieShoukang HuZi YeZengrui JinXunying LiuHelen MengPublished in: CoRR (2022)
Keyphrases
- feature extraction
- speech recognition systems
- recognition engine
- recognition rate
- feature vectors
- pattern recognition
- recognition accuracy
- image features
- speech recognition
- extracting features
- classification accuracy
- object recognition
- lexical features
- character recognition
- facial action units
- robust recognition
- highly discriminative
- discrimination power
- continuous speech recognition
- speaker recognition
- handwritten characters
- temporal structure
- recognition algorithm
- temporal information
- spatial and temporal
- keypoints
- action recognition
- feature set
- low level
- hidden markov models
- feature space