Temporal modulation normalization for robust speech feature extraction and recognition.
Xugang LuShigeki MatsudaMasashi UnokiSatoshi NakamuraPublished in: Multim. Tools Appl. (2011)
Keyphrases
- feature extraction
- preprocessing
- noisy environments
- recognition engine
- pattern recognition
- robust recognition
- feature extractor
- recognition rate
- partial occlusion
- recognition accuracy
- image classification
- keypoint detection
- speech recognition
- human recognition
- feature fusion
- feature selection
- temporal information
- spatial and temporal
- recognition algorithm
- speaker independent
- feature space
- spatio temporal
- speaker identification
- dimensionality reduction
- speech corpus
- principal component analysis
- frequency domain
- recognition process
- facial expression recognition
- temporal reasoning
- spoken language
- feature extraction and classification
- feature extractors
- temporal data
- object recognition
- cepstral coefficients
- computer vision