Skip to main content

USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS.

Publication ,  Conference
Chu, KM; Throckmorton, CS; Collins, LM; Mainsah, BO
Published in: Proceedings of meetings on acoustics. Acoustical Society of America
May 2018

In listening environments with room reverberation and background noise, cochlear implant (CI) users experience substantial difficulties in understanding speech. Because everyday environments have different combinations of reverberation and noise, there is a need to develop algorithms that can mitigate both effects to improve speech intelligibility. Desmond et al. (2014) developed a machine learning approach to mitigate the adverse effects of late reverberant reflections of speech signals by using a classifier to detect and remove affected segments in CI pulse trains. This study aimed to investigate the robustness of the reverberation mitigation algorithm in environments with both reverberation and noise. Sentence recognition tests were conducted in normal hearing listeners using vocoded speech with unmitigated and mitigated reverberant-only or noisy reverberant speech signals, across different reverberation times and noise types. Improvements in speech intelligibility were observed in mitigated reverberant-only conditions. However, mixed results were obtained in the mitigated noisy reverberant conditions as a reduction in speech intelligibility was observed for noise types whose spectra were similar to that of anechoic speech. Based on these results, the focus of future work is to develop a context-dependent approach that activates different mitigation strategies for different acoustic environments.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Proceedings of meetings on acoustics. Acoustical Society of America

DOI

EISSN

1939-800X

ISSN

1939-800X

Publication Date

May 2018

Volume

33

Issue

1

Start / End Page

050003
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Chu, K. M., Throckmorton, C. S., Collins, L. M., & Mainsah, B. O. (2018). USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS. In Proceedings of meetings on acoustics. Acoustical Society of America (Vol. 33, p. 050003). https://doi.org/10.1121/2.0000905
Chu, Kevin M., Chandra S. Throckmorton, Leslie M. Collins, and Boyla O. Mainsah. “USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS.” In Proceedings of Meetings on Acoustics. Acoustical Society of America, 33:050003, 2018. https://doi.org/10.1121/2.0000905.
Chu KM, Throckmorton CS, Collins LM, Mainsah BO. USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS. In: Proceedings of meetings on acoustics Acoustical Society of America. 2018. p. 050003.
Chu, Kevin M., et al. “USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS.Proceedings of Meetings on Acoustics. Acoustical Society of America, vol. 33, no. 1, 2018, p. 050003. Epmc, doi:10.1121/2.0000905.
Chu KM, Throckmorton CS, Collins LM, Mainsah BO. USING MACHINE LEARNING TO MITIGATE THE EFFECTS OF REVERBERATION AND NOISE IN COCHLEAR IMPLANTS. Proceedings of meetings on acoustics Acoustical Society of America. 2018. p. 050003.

Published In

Proceedings of meetings on acoustics. Acoustical Society of America

DOI

EISSN

1939-800X

ISSN

1939-800X

Publication Date

May 2018

Volume

33

Issue

1

Start / End Page

050003