A 94GHz millimeter-wave radar conduct speech enhancement based on signal subspace algorithm

Millimeter wave radar provides a promising alternative for conducting human speech. However, the 94 GHz radar speech signal are easy to be polluted by sources of noise which mainly include electromagnetic and channel noise. Thus, the quality of the radar speech was found to be unsatisfactory. In order to improve the quality of the radar speech, a signal subspace algorithm was used to remove the noise of radar speech. The method was evaluated by speech spectrogram. Experimental results show that the 94 GHz radar can effectively detect human speech signal, the combined noise of radar speech is greatly removed and the speech quality is improved significantly by the signal subspace algorithm.