AN ALGORITHM OF SPEECH RECAPTURE DETECTION

Recaptured speech can be used to deceive authentication systems for illegal purposes in speech/audio community, and thus it presents threats to security. Therefore, it is of great significance to investigate detection of recaptured speech. However, the related research efforts are still insuffi-cient. In this paper, we propose an algorithm to detect recaptured speech. The statistics of MFCC（Mel-Frequency Cepstral Coefficients）are employed as the features for SVM（Support Vector Ma-chine）and KNN (K-Nearest Neighbors) classification. Besides, SAE (Sparse Autoencoder) is also used for performance assessment. To simulate the real scenarioes of speech recapture process, va-rieties of recording devices, distances and environments are taken into consideration in the experi-ments. Experimental results show that accuracy of 99.67% can be achieved by increasing the diversi-ty of recaptured speech, indicating a good detection performance of the proposed algorithm.