| 초록 |
We report a new concept of machine learning-based speaker recognition via the flexible piezoelectric acoustic sensor (f-PAS) with high sensitivity. The resonant-type self-powered f-PAS was fabricated by mimicking the operating mechanism of the basilar membrane in the human cochlear. The f-PAS covered the voice frequency spectrum via the combination of its low quality (Q) factor and multi-resonant frequency tuning, exhibiting four to eight times higher sensitivity than the conventional condenser sensor. Our f-PAS acquired abundant voice information from the multi-channel sound inputs. The standard TIDIGITs dataset were recorded by the f-PAS and converted to frequency components by using a Fast Fourier Transform (FFT) and a Short-Time Fourier Transform (STFT) process. The machine learning based algorithm was designed by utilizing the most highest and second highest sensitivity data among multi-channel outputs, exhibiting outstanding speaker recognition rate of 97.5% with error rate reduction of 75%, compared to that of the reference condense-type MEMS microphone. |
