BACKGROUND
The cochlear implant technology is a well-known approach to help deaf patients hear speech again. It can improve speech intelligibility in quiet conditions; however, it still has room for improvement in noisy conditions. More recently, it has been proven that deep learning–based noise reduction (NR), such as noise classification and deep denoising autoencoder (NC+DDAE), can benefit the intelligibility performance of patients with cochlear implants compared to classical noise reduction algorithms.
OBJECTIVE
Following the successful implementation of the NC+DDAE model in our previous study, this study aimed to (1) propose an advanced noise reduction system using knowledge transfer technology, called NC+DDAE_T, (2) examine the proposed NC+DDAE_T noise reduction system using objective evaluations and subjective listening tests, and (3) investigate which layer substitution of the knowledge transfer technology in the NC+DDAE_T noise reduction system provides the best outcome.
METHODS
The knowledge transfer technology was adopted to reduce the number of parameters of the NC+DDAE_T compared with the NC+DDAE. We investigated which layer should be substituted using short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) scores, as well as t-distributed stochastic neighbor embedding to visualize the features in each model layer. Moreover, we enrolled ten cochlear implant users for listening tests to evaluate the benefits of the newly developed NC+DDAE_T.
RESULTS
The experimental results showed that substituting the middle layer (ie, the second layer in this study) of the noise-independent DDAE (NI-DDAE) model achieved the best performance gain regarding STOI and PESQ scores. Therefore, the parameters of layer three in the NI-DDAE were chosen to be replaced, thereby establishing the NC+DDAE_T. Both objective and listening test results showed that the proposed NC+DDAE_T noise reduction system achieved similar performances compared with the previous NC+DDAE in several noisy test conditions. However, the proposed NC+DDAE_T only needs a quarter of the number of parameters compared to the NC+DDAE.
CONCLUSIONS
This study demonstrated that knowledge transfer technology can help to reduce the number of parameters in an NC+DDAE while keeping similar performance rates. This suggests that the proposed NC+DDAE_T model may reduce the implementation costs of this noise reduction system and provide more benefits for cochlear implant users.
Noise power spectral density scaled SNR response estimation with restricted range search for sound source localisation using unmanned aerial vehicles