A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise

Syu Siang Wang, Yu Tsao, Hsiao Lan Sharon Wang, Ying Hui Lai, Lieber Po Hung Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper presents the clinical results of the application of a deep-learning-based noise reduction (NR) approach to improve speech intelligibility for cochlear implant (CI) recipients in the presence of competing speech noise. The deep denoising autoencoder (DDAE) model was used as a representative deep-learning-based NR model to reduce the noise components from the noisy input. The enhanced speech was subsequently played to six Mandarin-speaking CI recipients to perform recognition tests. All the subjects used their own clinical speech processors during testing. Two traditional NR approaches were also implemented to test the performance for a comparison. The Taiwan Mandarin version of the hearing in noise test (TMHINT) sentences were adopted and further corrupted by competing two talker speech noise at signal-to-noise ratio (SNR) levels of 0 and 5 dB. The experimental results showed that the DDAE NR approach can yield higher intelligibility scores than the two classical NR techniques in the presence of competing speech. The results of qualitative analysis further showed that the DDAE NR approach notably reduced the envelope distortions. The good results also suggest that the proposed DDAE NR approach can combine well with the existing CI processors to overcome the issue of degradation of speech perception, which is caused by competing speech noise.

Original languageEnglish
Title of host publicationProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages808-812
Number of pages5
ISBN (Electronic)9781538615423
DOIs
Publication statusPublished - 2018 Feb 5
Event9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
Duration: 2017 Dec 122017 Dec 15

Publication series

NameProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
Volume2018-February

Conference

Conference9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
CountryMalaysia
CityKuala Lumpur
Period17/12/1217/12/15

Fingerprint

Cochlear implants
Speech intelligibility
Noise abatement
Acoustic noise
Audition
Deep learning
Signal to noise ratio
Degradation
Testing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Information Systems
  • Signal Processing

Cite this

Wang, S. S., Tsao, Y., Wang, H. L. S., Lai, Y. H., & Li, L. P. H. (2018). A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 (pp. 808-812). (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017; Vol. 2018-February). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2017.8282144

A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise. / Wang, Syu Siang; Tsao, Yu; Wang, Hsiao Lan Sharon; Lai, Ying Hui; Li, Lieber Po Hung.

Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 808-812 (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017; Vol. 2018-February).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, SS, Tsao, Y, Wang, HLS, Lai, YH & Li, LPH 2018, A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise. in Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, vol. 2018-February, Institute of Electrical and Electronics Engineers Inc., pp. 808-812, 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, 17/12/12. https://doi.org/10.1109/APSIPA.2017.8282144
Wang SS, Tsao Y, Wang HLS, Lai YH, Li LPH. A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise. In Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 808-812. (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017). https://doi.org/10.1109/APSIPA.2017.8282144
Wang, Syu Siang ; Tsao, Yu ; Wang, Hsiao Lan Sharon ; Lai, Ying Hui ; Li, Lieber Po Hung. / A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 808-812 (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017).
@inproceedings{5652df2c06f448179f94cb615026c340,
title = "A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise",
abstract = "This paper presents the clinical results of the application of a deep-learning-based noise reduction (NR) approach to improve speech intelligibility for cochlear implant (CI) recipients in the presence of competing speech noise. The deep denoising autoencoder (DDAE) model was used as a representative deep-learning-based NR model to reduce the noise components from the noisy input. The enhanced speech was subsequently played to six Mandarin-speaking CI recipients to perform recognition tests. All the subjects used their own clinical speech processors during testing. Two traditional NR approaches were also implemented to test the performance for a comparison. The Taiwan Mandarin version of the hearing in noise test (TMHINT) sentences were adopted and further corrupted by competing two talker speech noise at signal-to-noise ratio (SNR) levels of 0 and 5 dB. The experimental results showed that the DDAE NR approach can yield higher intelligibility scores than the two classical NR techniques in the presence of competing speech. The results of qualitative analysis further showed that the DDAE NR approach notably reduced the envelope distortions. The good results also suggest that the proposed DDAE NR approach can combine well with the existing CI processors to overcome the issue of degradation of speech perception, which is caused by competing speech noise.",
author = "Wang, {Syu Siang} and Yu Tsao and Wang, {Hsiao Lan Sharon} and Lai, {Ying Hui} and Li, {Lieber Po Hung}",
year = "2018",
month = "2",
day = "5",
doi = "10.1109/APSIPA.2017.8282144",
language = "English",
series = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "808--812",
booktitle = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",

}

TY - GEN

T1 - A deep learning based noise reduction approach to improve speech intelligibility for cochlear implant recipients in the presence of competing speech noise

AU - Wang, Syu Siang

AU - Tsao, Yu

AU - Wang, Hsiao Lan Sharon

AU - Lai, Ying Hui

AU - Li, Lieber Po Hung

PY - 2018/2/5

Y1 - 2018/2/5

N2 - This paper presents the clinical results of the application of a deep-learning-based noise reduction (NR) approach to improve speech intelligibility for cochlear implant (CI) recipients in the presence of competing speech noise. The deep denoising autoencoder (DDAE) model was used as a representative deep-learning-based NR model to reduce the noise components from the noisy input. The enhanced speech was subsequently played to six Mandarin-speaking CI recipients to perform recognition tests. All the subjects used their own clinical speech processors during testing. Two traditional NR approaches were also implemented to test the performance for a comparison. The Taiwan Mandarin version of the hearing in noise test (TMHINT) sentences were adopted and further corrupted by competing two talker speech noise at signal-to-noise ratio (SNR) levels of 0 and 5 dB. The experimental results showed that the DDAE NR approach can yield higher intelligibility scores than the two classical NR techniques in the presence of competing speech. The results of qualitative analysis further showed that the DDAE NR approach notably reduced the envelope distortions. The good results also suggest that the proposed DDAE NR approach can combine well with the existing CI processors to overcome the issue of degradation of speech perception, which is caused by competing speech noise.

AB - This paper presents the clinical results of the application of a deep-learning-based noise reduction (NR) approach to improve speech intelligibility for cochlear implant (CI) recipients in the presence of competing speech noise. The deep denoising autoencoder (DDAE) model was used as a representative deep-learning-based NR model to reduce the noise components from the noisy input. The enhanced speech was subsequently played to six Mandarin-speaking CI recipients to perform recognition tests. All the subjects used their own clinical speech processors during testing. Two traditional NR approaches were also implemented to test the performance for a comparison. The Taiwan Mandarin version of the hearing in noise test (TMHINT) sentences were adopted and further corrupted by competing two talker speech noise at signal-to-noise ratio (SNR) levels of 0 and 5 dB. The experimental results showed that the DDAE NR approach can yield higher intelligibility scores than the two classical NR techniques in the presence of competing speech. The results of qualitative analysis further showed that the DDAE NR approach notably reduced the envelope distortions. The good results also suggest that the proposed DDAE NR approach can combine well with the existing CI processors to overcome the issue of degradation of speech perception, which is caused by competing speech noise.

UR - http://www.scopus.com/inward/record.url?scp=85047937784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047937784&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2017.8282144

DO - 10.1109/APSIPA.2017.8282144

M3 - Conference contribution

AN - SCOPUS:85047937784

T3 - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

SP - 808

EP - 812

BT - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -