Study On Real Time Speech Enhancement Of Cochlear Implant

The artificial cochlear implant is the only equipment that can effectively restore the hearing of the patients with moderate or severe hearing loss.It has been able to achieve very good results in the case of small ambient noise.However,if the surrounding environment is noisy,the effect of artificial cochlear implant is not satisfactory.Currently,the overseas artificial cochlear implant products account for a large share of the Chinese market and the price is very expensive.Therefore,it is very important for deaf patients with their families to explore the cochlear implant products and its speech enhancement algorithm.This paper,firstly,introduces the background and significance of speech enhancement algorithm of artificial cochlear implant and the current situation of domestic and abroad.Secondly,the principle of artificial cochlear implant and speech enhancement algorithm are introduced in detail.And then this paper puts forward a new speech enhancement algorithm which is based on speech endpoint detection algorithm on account of frequency domain features.The endpoint detection algorithm adopts the ratio between spectrum entropy for wavelet packet ERB sub-band and energy entropy for improvement of frequency domain.Therein,spectral entropy of wavelet packet ERB sub-band takes masking properties of human auditory and the signal frequency distribution difference between speech and noise into account;besides,the frequency-domain energy takes advantages of the energy difference between voice-frames and non-voice-frames.In addition,wiener filtering algorithm acquits real time data as well as uses the new parameters to distinguish voice segment and no-voice segment where noise spectrum is updated smoothly.Finally,a large number of experiments are carried out for the improved algorithm.At last,the experiment results demonstrate that the endpoint detection algorithm can be able to effectively distinguish between speech segments and no speech segments,leading to the improvement of speech enhancement in the case of low SNR and the guarantee of robustness as well as real-time of the algorithm.In contrast with the other two algorithms,the new approach to speech enhancement has a better effect.