Audio Feature and Correlation Function-Based Speech Recognition in FM Radio Broadcasting

The analysis and classification of audio signals are becoming increasingly important, especially in the age communication dissemination information through radio broadcasting systems. It is therefore essential that systems platforms available to monitor spread fake or fraudulent news. A speech feature-based correlation (SFC) algorithm a recognition framework developed this study, combining specific features performance real-time recognize based on human samples. include Mel frequency cepstral coefficient, gammatone spectral entropy, pitch. results illustrate advantages disadvantages each feature applied various sound groups. Furthermore, combined with design SFC further enhances system increases accuracy.