94 GHz Millimeter Wave Conducted Speech Enhancement

Abstract

The traditional microphone speech acquisition method has several limitations, such as short acquisition distance, non-directivity, weak ability to compensate for anti-acoustic noise, and poor sensitivity. As an alternative, our lab developed a new type of speech detection system using bio-radar. This novel speech detection method may effectively compensate for the shortcomings of the traditional microphone because of the special features of bio-radar. However, the detected radar speech is also corrupted by specific electromagnetic and ambient noises. Therefore, this study proposes a minimum mean-square error (MMSE) short-time spectral amplitude estimate algorithm to enhance radar captured speech. Because the proposed approach employs an optimal spectral amplitude estimator as well as a method to minimize the mean-square error of the log-spectra in enhancing noisy speech, this algorithm significantly reduces the colored residual noise. The enhanced radar speech was evaluated by both subjective and objective quality evaluation methods. The results demonstrate that the bio-radar can successfully detect speech signal and the proposed speech enhancement algorithm can improve radar captured speech quality.