e-journal
Gabor-Based Nonuniform Scale-Frequency Map for Environmental Sound Classification in Home Automation
This work presents a novel feature extraction approach called nonuniform scale-frequency map for environmental sound classification in home automation. For each audio frame, important atoms from the Gabor dictionary are selected by using the Matching Pursuit algorithm. After the system disregards phase and position information, the scale and frequency of the atoms are extracted to construct a scale-frequency map. Principle Component Analysis (PCA) and Linear Discriminate Analysis (LDA) are then applied to the scale-frequency map, subsequently generating the proposed feature. During the classification phase, a segment-level multiclass Support Vector Machine (SVM) is operated. Experiments on a 17-class
sound database indicate that the proposed approach can achieve an accuracy rate of 86.21%. Furthermore, a comparison reveals that the proposed approach is superior to the other time-frequency methods.
Note to Practitioners—This work presents a robust environmental sound recognition system for home automation. Specific home automation services, such as security surveillance, safety monitoring, object handling, or appliance control, can be activated via computers based on identified sound classes. This study mathematically characterizes the input signal and converts it into a numeric audio feature. Subsequently, inappropriate audio features that may degrade system performance are filtered out by statistical methods. In the final stage, an estimator is used for classifying audio features.
Index Terms—Environmental sound classification, feature extraction, Gabor function, home automation, matching pursuit (MP), nonuniform scale-frequency map.
Tidak ada salinan data
Tidak tersedia versi lain