Objective : In a cochlear implant (CI) speech processor, noise reduction (NR) is a critical component for enabling CI users to attain improved speech perception under noisy conditions. Identifying an effective NR approach has long been a key topic in CI research. Method : Recently, a deep denoising autoencoder (DDAE) based NR approach was proposed and shown to be effective in restoring clean speech from noisy observations. It was also shown that DDAE could provide better performance than several existing NR methods in standardized objective evaluations. Following this success with normal speech, this paper further investigated the performance of DDAE-based NR to improve the intelligibility of envelope-based vocoded speech, which simulates speech signal processing in existing CI devices. Results : We compared the performance of speech intelligibility between DDAE-based NR and conventional single-microphone NR approaches using the noise vocoder simulation. The results of both objective evaluations and listening test showed that, under the conditions of nonstationary noise distortion, DDAE-based NR yielded higher intelligibility scores than conventional NR approaches. Conclusion and significance : This study confirmed that DDAE-based NR could potentially be integrated into a CI processor to provide more benefits to CI users under noisy conditions.

A Deep Denoising Autoencoder Approach to Improving the Intelligibility of Vocoded Speech in Cochlear Implant Simulation

Objective We investigate the clinical effectiveness of a novel deep learning-based noise reduction (NR) approach under noisy conditions with challenging noise types at low signal to noise ratio (SNR) levels for Mandarin-speaking cochlear implant (CI) recipients. Design The deep learning-based NR approach used in this study consists of two modules: noise classifier (NC) and deep denoising autoencoder (DDAE), thus termed (NC + DDAE). In a series of comprehensive experiments, we conduct qualitative and quantitative analyses on the NC module and the overall NC + DDAE approach. Moreover, we evaluate the speech recognition performance of the NC + DDAE NR and classical single-microphone NR approaches for Mandarin-speaking CI recipients under different noisy conditions. The testing set contains Mandarin sentences corrupted by two types of maskers, two-talker babble noise, and a construction jackhammer noise, at 0 and 5 dB SNR levels. Two conventional NR techniques and the proposed deep learning-based approach are used to process the noisy utterances. We qualitatively compare the NR approaches by the amplitude envelope and spectrogram plots of the processed utterances. Quantitative objective measures include (1) normalized covariance measure to test the intelligibility of the utterances processed by each of the NR approaches; and (2) speech recognition tests conducted by nine Mandarin-speaking CI recipients. These nine CI recipients use their own clinical speech processors during testing. Results The experimental results of objective evaluation and listening test indicate that under challenging listening conditions, the proposed NC + DDAE NR approach yields higher intelligibility scores than the two compared classical NR techniques, under both matched and mismatched training-testing conditions. Conclusions When compared to the two well-known conventional NR techniques under challenging listening condition, the proposed NC + DDAE NR approach has superior noise suppression capabilities and gives less distortion for the key speech envelope information, thus, improving speech recognition more effectively for Mandarin CI recipients. The results suggest that the proposed deep learning-based NR approach can potentially be integrated into existing CI signal processors to overcome the degradation of speech perception caused by noise.

Deep Learning-Based Noise Reduction Approach to Improve Speech Intelligibility for Cochlear Implant Recipients.

Spectral smearing causes, at least partially, that cochlear implant (CI) users require a higher signal-to-noise ratio to obtain the same speech intelligibility as normal hearing listeners. A spectral contrast enhancement (SCE) algorithm has been designed and evaluated as an additional feature for a standard CI strategy. The algorithm keeps the most prominent peaks within a speech signal constant while attenuating valleys in the spectrum. The goal is to partly compensate for the spectral smearing produced by the limited number of stimulation electrodes and the overlap of electrical fields produced in CIs. Twelve CI users were tested for their speech reception threshold (SRT) using the standard CI coding strategy with and without SCE. No significant differences in SRT were observed between conditions. However, an analysis of the electrical stimulation patterns shows a reduction in stimulation current when using SCE. In a second evaluation, 12 CI users were tested in a similar configuration of the SCE strategy with the stimulation being balanced between the SCE and the non-SCE variants such that the loudness perception delivered by the strategies was the same. Results show a significant improvement in SRT of 0.57 dB (p < 0.0005) for the SCE algorithm.

Spectral contrast enhancement improves speech intelligibility in noise for cochlear implants

Purpose The aim of this article is to summarize recent published and unpublished research from our 2 laboratories on improving speech understanding in complex listening environments by listeners fi...

https://pubs.asha.org/doi/pdf/10.1044/2017_JSLHR-H-17-0035

Speech Understanding in Complex Listening Environments by Listeners Fit With Cochlear Implants

The benefits of combining a cochlear implant (CI) and a hearing aid (HA) in opposite ears on speech perception were examined in 15 adult unilateral CI recipients who regularly use a contralateral HA. A within-subjects design was carried out to assess speech intelligibility testing, listening effort ratings, and a sound quality questionnaire for the conditions CI alone, CIHA together, and HA alone when applicable. The primary outcome of bimodal benefit, defined as the difference between CIHA and CI, was statistically significant for speech intelligibility in quiet as well as for intelligibility in noise across tested spatial conditions. A reduction in effort on top of intelligibility at the highest tested signal-to-noise ratio was found. Moreover, the bimodal listening situation was rated to sound more voluminous, less tinny, and less unpleasant than CI alone. Listening effort and sound quality emerged as feasible and relevant measures to demonstrate bimodal benefit across a clinically representative range of bimodal users. These extended dimensions of speech perception can shed more light on the array of benefits provided by complementing a CI with a contralateral HA.

The Benefits of Bimodal Aiding on Extended Dimensions of Speech Perception: Intelligibility, Listening Effort, and Sound Quality.

Objective 
To investigate the performance of monaural and binaural beamforming technology with an additional noise reduction algorithm, in cochlear implant recipients.
Method 
This experimental study was conducted as a single subject repeated measures design within a large German cochlear implant centre. Twelve experienced users of an Advanced Bionics HiRes90K or CII implant with a Harmony speech processor were enrolled. The cochlear implant processor of each subject was connected to one of two bilaterally placed state-of-the-art hearing aids (Phonak Ambra) providing three alternative directional processing options: an omnidirectional setting, an adaptive monaural beamformer, and a binaural beamformer. A further noise reduction algorithm (ClearVoice) was applied to the signal on the cochlear implant processor itself. The speech signal was presented from 0° and speech shaped noise presented from loudspeakers placed at ±70°, ±135° and 180°. The Oldenburg sentence test was used to determine the signal-to-noise ratio at which subjects scored 50% correct.
Results 
Both the adaptive and binaural beamformer were significantly better than the omnidirectional condition (5.3 dB±1.2 dB and 7.1 dB±1.6 dB (p<0.001) respectively). The best score was achieved with the binaural beamformer in combination with the ClearVoice noise reduction algorithm, with a significant improvement in SRT of 7.9 dB±2.4 dB (p<0.001) over the omnidirectional alone condition.
Conclusions 
The study showed that the binaural beamformer implemented in the Phonak Ambra hearing aid could be used in conjunction with a Harmony speech processor to produce substantial average improvements in SRT of 7.1 dB. The monaural, adaptive beamformer provided an averaged SRT improvement of 5.3 dB.

/pdf/advanced-beamformers-for-cochlear-implant-users-acute-43pbvtmgrl.pdf

Advanced Beamformers for Cochlear Implant Users: Acute Measurement of Speech Perception in Challenging Listening Conditions

Speech intelligibility in noisy environments remains a difficult challenge for cochlear implant (CI) users. Signal processing techniques such as beamforming and singlemicrophone noise reduction can partially alleviate this problem. We tested the effect of one adaptive monaural and one binaural beamformer by hearing-aid manufacturer Phonak on speech intelligibility (SI) in largely diffuse noise in a group of 12 unilateral users of the Advanced Bionics (AB) Harmony speech processor. Both beamformers were further combined with AB’s noise reduction algorithm ClearVoice. Two test sessions were performed per subject. In session A, we found significant benefits for both the adaptive beamformer and ClearVoice, yielding a combined SRT improvement of 6.1dB. Session B revealed a further benefit for the binaural beamformer. Together with ClearVoice, the resultant SRT improvement over the unprocessed signal was 7.86dB.

Improved Speech Intelligibility With Cochlear Implants Using State-of-the-Art Noise Reduction Algorithms.

The invention relates to an auditory prosthesis device for neural stimulation of a patient's hearing, comprising means (20) for providing an input audio signal, a sound processor (24) for generating a neural stimulation signal from the input audio signal, an implantable stimulation assembly (12) for stimulation of the patient's hearing according to the neural stimulation signal, and a control unit (54) for controlling the sound processor, the control unit being adapted to control at least one parameter used in the generation of the neural stimulation signal from the input audio signal such that, during an adjustment period, the value of the at least one parameter is automatically changed from a first value to a second value as a function of the time having passed since a reference point in time.

Method and system for neural hearing stimulation

There is provided a hearing assistance system, comprising an audio streaming device, a first hearing device for stimulating a first ear of a user, and a second hearing device for stimulating a second ear of the user, the audio streaming device comprising an audio input interface for receiving an input stereo audio signal, a unit for analyzing the input stereo audio signal in order to determine at least one azimuthal localization cue by comparing the two channels of the stereo signal, a unit for processing the input stereo audio signal in order to produce an output stereo audio signal, and a unit for supplying one channel of the output stereo audio signal to the first hearing device and for supplying the other channel of the output stereo audio signal to the second hearing device.

Stefan Fredelake

Papers

Advanced Beamformers for Cochlear Implant Users: Acute Measurement of Speech Perception in Challenging Listening Conditions

Improved Speech Intelligibility With Cochlear Implants Using State-of-the-Art Noise Reduction Algorithms.

Method and system for neural hearing stimulation

Hearing assistance system