Automatic detection of malicious sound using segmental two-dimensional mel-frequency cepstral coefficients and histograms of oriented gradients.
Myung Jong KimYounggwan KimJaeDeok LimHoirin KimPublished in: ACM Multimedia (2010)
Keyphrases
- automatic detection
- histograms of oriented gradients
- acoustic features
- human detection
- pedestrian detection
- object detection
- three dimensional
- speaker recognition
- local binary pattern
- human body
- speech signal
- hidden markov models
- speaker identification
- action recognition
- speaker verification
- music information retrieval
- visual features
- surveillance system
- spectral features
- co occurrence
- machine learning
- pattern recognition
- automatic speech recognition
- feature descriptors
- detection rate
- gaussian mixture model
- similarity measure
- speech recognition