Speech Understanding Performance of Cochlear Implant Subjects Using Time–Frequency Masking-Based Noise Reduction

2012 ◽  
Vol 59 (5) ◽  
pp. 1364-1373 ◽  
Author(s):  
O. ur Rehman Qazi ◽  
B. van Dijk ◽  
M. Moonen ◽  
J. Wouters
Keyword(s):  
Cochlear Implant ◽  
Noise Reduction ◽  
Speech Understanding ◽  
Time Frequency

Improved Environment-Aware–Based Noise Reduction System for Cochlear Implant Users Based on Knowledge Transfer Approach (Preprint)

2020 ◽  
Author(s):  
Lieber Po-Hung Li ◽  
Ji-Yan Han ◽  
Wei-Zhong Zheng ◽  
Ren-Jie Huang ◽  
Ying-Hui Lai
Keyword(s):  
Knowledge Transfer ◽  
Cochlear Implant ◽  
Noise Reduction ◽  
Speech Intelligibility ◽  
Middle Layer ◽  
Successful Implementation ◽  
Perceptual Evaluation ◽  
Reduction System ◽  
Listening Tests ◽  
Implementation Costs

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.

scholarly journals Noise power spectral density scaled SNR response estimation with restricted range search for sound source localisation using unmanned aerial vehicles

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Benjamin Yen ◽  
Yusuke Hioka
Keyword(s):  
Spectral Density ◽  
Noise Reduction ◽  
Power Spectral Density ◽  
Sound Source ◽  
Processing Algorithm ◽  
Post Processing ◽  
Time Frequency ◽  
Distance Error ◽  
Rotor Noise ◽  
Power Spectral

Abstract A method to locate sound sources using an audio recording system mounted on an unmanned aerial vehicle (UAV) is proposed. The method introduces extension algorithms to apply on top of a baseline approach, which performs localisation by estimating the peak signal-to-noise ratio (SNR) response in the time-frequency and angular spectra with the time difference of arrival information. The proposed extensions include a noise reduction and a post-processing algorithm to address the challenges in a UAV setting. The noise reduction algorithm reduces influences of UAV rotor noise on localisation performance, by scaling the SNR response using power spectral density of the UAV rotor noise, estimated using a denoising autoencoder. For the source tracking problem, an angular spectral range restricted peak search and link post-processing algorithm is also proposed to filter out incorrect location estimates along the localisation path. Experimental results show the proposed extensions yielded improvements in locating the target sound source correctly, with a 0.0064–0.175 decrease in mean haversine distance error across various UAV operating scenarios. The proposed method also shows a reduction in unexpected location estimations, with a 0.0037–0.185 decrease in the 0.75 quartile haversine distance error.

AzBio Speech Understanding Performance in Quiet and Noise in High Performing Cochlear Implant Users

2018 ◽  
Vol 39 (5) ◽  
pp. 571-575 ◽  
Author(s):  
Jason A. Brant ◽  
Steven J. Eliades ◽  
Hannah Kaufman ◽  
Jinbo Chen ◽  
Michael J. Ruckenstein
Keyword(s):  
Cochlear Implant ◽  
Speech Understanding ◽  
High Performing

scholarly journals Neural envelope tracking as a measure of speech understanding in cochlear implant users

2018 ◽  
Author(s):  
Eline Verschueren ◽  
Ben Somers ◽  
Tom Francart
Keyword(s):  
Cochlear Implant ◽  
Cochlear Implants ◽  
Closed Loop ◽  
Objective Measure ◽  
Speech Understanding ◽  
Envelope Tracking ◽  
Actual Speech ◽  
Speech Envelope ◽  
Electroencephalogram Eeg ◽  
Automatic Fitting

ABSTRACTThe speech envelope is essential for speech understanding and can be reconstructed from the electroencephalogram (EEG) recorded while listening to running speech. This so-called neural envelope tracking has been shown to relate to speech understanding in normal hearing listeners, but has barely been investigated in persons wearing cochlear implants (CI). We investigated the relation between speech understanding and neural envelope tracking in CI users.EEG was recorded in 8 CI users while they listened to a story. Speech understanding was varied by changing the intensity of the presented speech. The speech envelope was reconstructed from the EEG using a linear decoder and then correlated with the envelope of the speech stimulus as a measure of neural envelope tracking which was compared to actual speech understanding.This study showed that neural envelope tracking increased with increasing speech understanding in every participant. Furthermore behaviorally measured speech understanding was correlated with participant specific neural envelope tracking results indicating the potential of neural envelope tracking as an objective measure of speech understanding in CI users. This could enable objective and automatic fitting of CIs and pave the way towards closed-loop CIs that adjust continuously and automatically to individual CI users.

scholarly journals An improved time–frequency noise reduction method using a psycho-acoustic Mel model

2018 ◽  
Vol 79 ◽  
pp. 199-212 ◽  
Author(s):  
Samir Ouelha ◽  
Abdeldjalil Aïssa-El-Bey ◽  
Boualem Boashash
Keyword(s):  
Noise Reduction ◽  
Reduction Method ◽  
Frequency Noise ◽  
Time Frequency
Sign in / Sign up

Export Citation Format

Share Document