Design of an ultra-low Power MFCC Feature Extraction Circuit with Embedded Speech Activity Detector

Mel frequency cepstrum coefficient (MFCC) is widely used in the feature extraction of speech signals. In practical applications, the feature extraction circuit does not need to work at non-speech conditions. By extracting and reusing the data of framing operation in MFCC, we propose a speech activity detector (SAD) based on the amplitude and zero-crossing rate of the speech to distinguish differen...