IDENTIFICATION OF RECORDED AUDIO LOCATION USING ACOUSTIC ENVIRONMENT CLASSIFICATION

DIGITAL SIGNAL PROCESSING

There are many artifact and different distortions present in the recording. The reverberation depends on the volume properties of the room and it causes the calumniation of the recording. The background noise depends on the unnecessary audio source activities present in the evident recording. For audio to be considered as proof in a court, its authenticity must be verified. A blind deconvolution method based on FIR filtering and overlap add method is used to estimate reverberation time. Particle filtering is used to estimate the background noise. Feature extraction is done by using MFCC approach. The 128 Dimensional feature vector is the addition of features from acoustic reverberation and background noise and the higher order statistics. SVM classifier is used for classification of the environments. The performance of the system is checked using audio recordings dataset. The SVM classifier provides best results for the trained dataset and moderate results for untrained dataset.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.