An End-to-End Deep Learning Sound Coding Strategy for Cochlear Implants

Cochlear implant (CI) users struggle to understand speech in noisy conditions. In this work, we propose an end-to-end speech coding and denoising sound coding strategy that estimates the electrodograms from the raw audio captured by the microphone. We compared this approach to a classic Wiener filter and TasNet to assess its potential benefits in the context of electric hearing. The performance of the network is assessed by means of noise reduction performance (signal-to-noise-ratio improvement) and objective speech intelligibility measures. Furthermore, speech intelligibility was measured in 5 CI users to assess the potential benefits of each of the investigated algorithms. Results suggest that the speech performance of the tested group seemed to be equally good using our method compared to the front-end speech enhancement algorithm.

The Spatial Selective Auditory Attention of Cochlear Implant Users in Different Conversational Sound Levels

In multi-speaker environments, cochlear implant (CI) users may attend to a target sound source in a different manner from normal hearing (NH) individuals during a conversation. This study attempted to investigate the effect of conversational sound levels on the mechanisms adopted by CI and NH listeners in selective auditory attention and how it affects their daily conversation. Nine CI users (five bilateral, three unilateral, and one bimodal) and eight NH listeners participated in this study. The behavioral speech recognition scores were collected using a matrix sentences test, and neural tracking to speech envelope was recorded using electroencephalography (EEG). Speech stimuli were presented at three different levels (75, 65, and 55 dB SPL) in the presence of two maskers from three spatially separated speakers. Different combinations of assisted/impaired hearing modes were evaluated for CI users, and the outcomes were analyzed in three categories: electric hearing only, acoustic hearing only, and electric + acoustic hearing. Our results showed that increasing the conversational sound level degraded the selective auditory attention in electrical hearing. On the other hand, increasing the sound level improved the selective auditory attention for the acoustic hearing group. In the NH listeners, however, increasing the sound level did not cause a significant change in the auditory attention. Our result implies that the effect of the sound level on selective auditory attention varies depending on the hearing modes, and the loudness control is necessary for the ease of attending to the conversation by CI users.

Correlation between Speech Perception Outcomes after Cochlear Implantation and Postoperative Acoustic and Electric Hearing Thresholds

The reliable prediction of cochlear implant (CI) speech perception outcomes is highly relevant and can facilitate the monitoring of postoperative hearing performance. To date, multiple audiometric, demographic, and surgical variables have shown some degree of correlation with CI speech perception outcomes. In the present study, postsurgical acoustic and electric hearing thresholds that are routinely assessed in clinical practice were compared to CI speech perception outcomes in order to reveal possible markers of postoperative cochlear health. A total of 237 CI recipients were included in this retrospective monocentric study. An analysis of the correlation of postoperative pure-tone averages (PTAs) and electric CI fitting thresholds (T-/C-levels) with speech perception scores for monosyllabic words in quiet was performed. Additionally, a correlation analysis was performed for postoperative acoustic thresholds in intracochlear electrocochleography (EcochG) and speech recognition scores in a smaller group (n = 14). The results show that neither postoperative acoustic hearing thresholds nor electric thresholds correlate with postoperative speech perception outcomes, and they do not serve as independent predictors of speech perception outcomes. By contrast, the postoperative intracochlear total EcochG response was significantly correlated with speech perception. Since the EcochG recordings were only performed in a small population, a large study is required to clarify the usefulness of this promising predictive parameter.

Evaluating the Impact of Age, Acoustic Exposure, and Electrical Stimulation on Binaural Sensitivity in Adult Bilateral Cochlear Implant Patients

Deafness in both ears is highly disruptive to communication in everyday listening situations. Many individuals with profound deafness receive bilateral cochlear implants (CIs) to gain access to spatial cues used in localization and speech understanding in noise. However, the benefit of bilateral CIs, in particular sensitivity to interaural time and level differences (ITD and ILDs), varies among patients. We measured binaural sensitivity in 46 adult bilateral CI patients to explore the relationship between binaural sensitivity and three classes of patient-related factors: age, acoustic exposure, and electric hearing experience. Results show that ILD sensitivity increased with shorter years of acoustic exposure, younger age at testing, or an interaction between these factors, moderated by the duration of bilateral hearing impairment. ITD sensitivity was impacted by a moderating effect between years of bilateral hearing impairment and CI experience. When age at onset of deafness was treated as two categories (<18 vs. >18 years of age), there was no clear effect for ILD sensitivity, but some differences were observed for ITD sensitivity. Our findings imply that maximal binaural sensitivity is obtained by listeners with a shorter bilateral hearing impairment, a longer duration of CI experience, and potentially a younger age at testing. 198/200.