Real-World Speech/Non-Speech Audio Classification Based on Sparse Representation Features and GPCs.
Ziqiang ShiJiqing HanTieran ZhengPublished in: INTERSPEECH (2011)
Keyphrases
- sparse representation
- dictionary learning
- audio features
- acoustic signals
- image classification
- mel frequency cepstral coefficients
- feature extraction
- cepstral features
- audio visual
- real world
- feature set
- speaker identification
- audio stream
- feature vectors
- visual speech
- speech music discrimination
- speech recognition
- sparse coding
- speech signal
- feature space
- visual features
- face recognition
- dimensionality reduction
- feature analysis
- compressive sensing
- high dimensionality
- signal processing
- acoustic features
- image features
- broadcast news
- basis vectors
- compressed sensing
- emotion recognition
- image patches
- machine learning
- gaussian mixture model
- svm classifier
- high dimensional data
- decision trees
- pattern recognition
- sparse reconstruction
- audio signal
- regularized least squares
- random projections
- support vector machine
- sparse codes
- principal component analysis
- data mining
- nearest neighbor
- model selection
- test images
- feature subset