A New Approach for Noise Suppression in Cochlear Implants: A Single-Channel Noise Reduction Algorithm

Evaluation of a personalized auditory-cognitive training on the improvement of speech understanding in noise in cochlear implanted patients

OBJECTIVE

The cochlear implant is a commonly used implantable device for the auditory rehabilitation of severe bilateral sensorineural hearing loss. The effectiveness of the implant, depends on many factors, including intensive auditory training, which is crucial. Intelligibility in a noisy environment is a current issue and poses a major difficulty for implanted patients. The aim of this study is to evaluate the improvement in auditory performance in noise among cochlear implant patients who underwent personalized auditory-cognitive training for speech understanding tasks in noise.

DESIGN

This was a prospective study involving cochlear implanted patients divided into two groups. One group underwent auditory training in a noisy environment at home for 2 months (G1) while the other group served as a control (G0). A test of intelligibility performance in noise was conducted at inclusion and two months later.

RESULTS

52 patients were included in the study. The trained group, G1, showed a significant improvement with an increase of 4.8 dB in signal-to-noise ratio (SNR) between the two tests (P < 0.01). There was no significant improvement in the control group (G0) (P = 0.756).

CONCLUSIONS

This study demonstrated a significantly positive impact of personalized auditory training in a noisy environment for cochlear implant patients.

Knowledge, attitude, and practice toward cochlear implants among deaf patients who received cochlear implants

Despite the growing use of cochlear implants in deaf patients, there is a lack of data on their knowledge, attitude, and practice (KAP) toward cochlear implants. This study aimed to investigate the KAP toward cochlear implants among deaf patients who received cochlear implants. A web-based cross-sectional study was conducted between August 2022 and December 2022 among deaf patients who had received cochlear implants. A self-administered questionnaire was used to collect demographic characteristics and KAP scores. A total of 526 participants were enrolled; 54.18% were female, 65.40% were above 60 years old, and 61.03% were surveyed at less than 3 years after implantation. The mean knowledge, attitude, and practice scores were 8.15 ± 2.18 (possible range: 0-10), 43.63 ± 6.98 (possible range: 12-60), and 41.11 ± 7.42 (possible range: 11-55), respectively, indicating good knowledge, moderate attitude and practice. Multivariable logistic regression analysis showed that attitude [odd ratio (OR) = 1.24, 95% confidence interval (CI) 1.18-1.29, P < 0.001] and unemployment (OR = 0.33, 95% CI 0.17-0.63, P = 0.001) were independently associated with practice. Path analysis showed that knowledge directly influenced attitude (β = 0.93, 95% CI 0.61-1.19, P < 0.001), attitude directly influenced practice (β = 0.53, 95% CI 0.46-0.61, P < 0.001), and knowledge directly (β = 0.77, 95% CI 0.53-1.01, P < 0.001) and indirectly (β = 0.50, 95% CI 0.34-0.66, P < 0.001) influenced practice. Deaf patients who received cochlear implants showed good knowledge, moderate attitude and practice toward cochlear implants. Knowledge should be strengthened to improve attitude and practice toward cochlear implants, which could translate into realistic expectations toward cochlear implants devices and proper care and maintenance.

Patient perspectives on the need for improved hearing rehabilitation: A qualitative survey study of German cochlear implant users

Background

The electrical cochlear implant (eCI) partially restores hearing in individuals affected by profound hearing impairment (HI) or deafness. However, the limited resolution of sound frequency coding with eCIs limits hearing in daily situations such as group conversations. Current research promises future improvements in hearing restoration which may involve gene therapy and optical stimulation of the auditory nerve, using optogenetics. Prior to the potential clinical translation of these technologies, it is critical that patients are engaged in order to align future research agendas and technological advancements with their needs.

Methods

Here, we performed a survey study with hearing impaired, using an eCI as a means of hearing rehabilitation. We distributed a questionnaire to 180 adult patients from the University Medical Center Göttingen's Department of Otolaryngology who were actively using an eCI for 6 months or more during the time of the survey period. Questions revolved around patients needs, and willingness to accept hypothetical risks or drawbacks associated with an optical CI (oCI).

Results

Eighty-one participants responded to the questionnaire; 68% were greater than 60 years of age and 26% had bilateral eCIs. Participants expressed a need for improving the performance beyond that experienced with their current eCI. Primarily, they desired improved speech comprehension in background noise, greater ability to appreciate music, and more natural sound impression. They expressed a willingness for engaging with new technologies for improved hearing restoration. Notably, participants were least concerned about hypothetically receiving a gene therapy necessary for the oCI implant; but expressed greater reluctance to hypothetically receiving an implant that had yet to be evaluated in a human clinical trial.

Conclusion

This work provides a preliminary step in engaging patients in the development of a new technology that has the potential to address the limitations of electrical hearing rehabilitation.

Listening Effort in Cochlear Implant Users: The Effect of Speech Intelligibility, Noise Reduction Processing, and Working Memory Capacity on the Pupil Dilation Response

PURPOSE

This study aimed to evaluate the effect of speech recognition performance, working memory capacity (WMC), and a noise reduction algorithm (NRA) on listening effort as measured with pupillometry in cochlear implant (CI) users while listening to speech in noise.

METHOD

Speech recognition and pupil responses (peak dilation, peak latency, and release of dilation) were measured during a speech recognition task at three speech-to-noise ratios (SNRs) with an NRA in both on and off conditions. WMC was measured with a reading span task. Twenty experienced CI users participated in this study.

RESULTS

With increasing SNR and speech recognition performance, (a) the peak pupil dilation decreased by only a small amount, (b) the peak latency decreased, and (c) the release of dilation after the sentences increased. The NRA had no effect on speech recognition in noise or on the peak or latency values of the pupil response but caused less release of dilation after the end of the sentences. A lower reading span score was associated with higher peak pupil dilation but was not associated with peak latency, release of dilation, or speech recognition in noise.

CONCLUSIONS

In CI users, speech perception is effortful, even at higher speech recognition scores and high SNRs, indicating that CI users are in a chronic state of increased effort in communication situations. The application of a clinically used NRA did not improve speech perception, nor did it reduce listening effort. Participants with a relatively low WMC exerted relatively more listening effort but did not have better speech reception thresholds in noise.

Deep Learning-Based Speech Enhancement With a Loss Trading Off the Speech Distortion and the Noise Residue for Cochlear Implants

The cochlea plays a key role in the transmission from acoustic vibration to neural stimulation upon which the brain perceives the sound. A cochlear implant (CI) is an auditory prosthesis to replace the damaged cochlear hair cells to achieve acoustic-to-neural conversion. However, the CI is a very coarse bionic imitation of the normal cochlea. The highly resolved time-frequency-intensity information transmitted by the normal cochlea, which is vital to high-quality auditory perception such as speech perception in challenging environments, cannot be guaranteed by CIs. Although CI recipients with state-of-the-art commercial CI devices achieve good speech perception in quiet backgrounds, they usually suffer from poor speech perception in noisy environments. Therefore, noise suppression or speech enhancement (SE) is one of the most important technologies for CI. In this study, we introduce recent progress in deep learning (DL), mostly neural networks (NN)-based SE front ends to CI, and discuss how the hearing properties of the CI recipients could be utilized to optimize the DL-based SE. In particular, different loss functions are introduced to supervise the NN training, and a set of objective and subjective experiments is presented. Results verify that the CI recipients are more sensitive to the residual noise than the SE-induced speech distortion, which has been common knowledge in CI research. Furthermore, speech reception threshold (SRT) in noise tests demonstrates that the intelligibility of the denoised speech can be significantly improved when the NN is trained with a loss function bias to more noise suppression than that with equal attention on noise residue and speech distortion.