Noise robust audio surveillance using reduced spectrogram image feature and one-against-all SVM

Computer Science

• Support Vector Machine 100%
• Classification Accuracy 100%
• Mel-Frequency Cepstral Coefficients 100%
• image feature 100%
• Feature Extraction 66%
• Directed Acyclic Graph 66%
• Noisy Condition 66%
• Classification Method 33%
• Classification Technique 33%
• Subclasses 33%
• Feature Vector 33%
• Statistical Distribution 33%
• Image Representation 33%
• Signal Property 33%
• Block Distribution 33%

Engineering

• Support Vector Machine 100%
• Spectrogram 100%
• Classification Accuracy 50%
• Feature Extraction 33%
• Classification Method 16%
• Similarity 16%
• Dimensionality 16%
• Feature Vector 16%
• Statistical Distribution 16%
• Sound Signal 16%
• Image Representation 16%
• Signal Property 16%