When a transducer is put on an aural cartilage, the transmitted vibration generates sound in the external auditory canal (i.e., cartilage conduction). A hearing device based on the cartilage conduction does not need occluding the external auditory canal. When an active noise control can adapt only to unwanted noise, the device enables natural conversations with unprocessed voice in the noisy environment (selective cancelation). To accomplish the selective cancelation, we proposed delayed-X harmonics synthesizer (DXHS) algorithm to minimize the damage for the speech quality. A target noise in this study was bandpass noise through a gammatone filter (center frequency: 500 Hz) overlapping the speech spectrum. After tracing the spectral envelope of the noise by using linear predictive coding (LPC), the DXHS outputted five pure tones distributed around the peak of envelope, and each step size parameter was adjusted according to the amplitude of the envelope. As results, our proposed method showed the noise reduction of 11.3 dB maintaining the speech quality in the computer simulations. During the adaptation, the step size adjustment enabled round off the spectral peak of the bandpass noise to avoid sharpening it.
Read full abstract