Speech enhancement based on neural networks applied to cochlear implant coding strategies

Federico Bolner; Tobias Goehring; Jessica Monaghan; Bas Van Dijk; Jan Wouters; Stefan Bleeck

doi:10.1109/ICASSP.2016.7472933

Speech enhancement based on neural networks applied to cochlear implant coding strategies

Federico Bolner^*, Tobias Goehring, Jessica Monaghan, Bas Van Dijk, Jan Wouters, Stefan Bleeck

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

35 Citations (Scopus)

Abstract

Traditionally, algorithms that attempt to significantly improve speech intelligibility in noise for cochlear implant (CI) users have met with limited success, particularly in the presence of a fluctuating masker. In the present study, a speech enhancement algorithm integrating an artificial neural network (NN) into CI coding strategies is proposed. The algorithm decomposes the noisy input signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the NN to produce an estimation of which CI channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is then used accordingly to retain a subset of channels for electrical stimulation, as in traditional n-of-m coding strategies. The proposed algorithm was tested with 10 normal-hearing participants listening to CI noise-vocoder simulations against a conventional Wiener filter based enhancement algorithm. Significant improvements in speech intelligibility in stationary and fluctuating noise were found over both unprocessed and Wiener filter processed conditions.

Original language	English
Title of host publication	2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	6520-6524
Number of pages	5
ISBN (Electronic)	9781479999880
DOIs	https://doi.org/10.1109/ICASSP.2016.7472933
Publication status	Published - 18 May 2016
Externally published	Yes
Event	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China Duration: 20 Mar 2016 → 25 Mar 2016

Publication series

Name	International Conference on Acoustics Speech and Signal Processing ICASSP
Publisher	IEEE
ISSN (Print)	1520-6149

Other

Other	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/Territory	China
City	Shanghai
Period	20/03/16 → 25/03/16

Keywords

Cochlear implants
machine learning
neural networks
noise reduction
speech enhancement

Access to Document

10.1109/ICASSP.2016.7472933

Cite this

Bolner, F., Goehring, T., Monaghan, J., Van Dijk, B., Wouters, J., & Bleeck, S. (2016). Speech enhancement based on neural networks applied to cochlear implant coding strategies. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (pp. 6520-6524). Article 7472933 (International Conference on Acoustics Speech and Signal Processing ICASSP). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2016.7472933

Bolner, Federico ; Goehring, Tobias ; Monaghan, Jessica et al. / Speech enhancement based on neural networks applied to cochlear implant coding strategies. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2016. pp. 6520-6524 (International Conference on Acoustics Speech and Signal Processing ICASSP).

@inproceedings{f03edaf46b8e4417942398a60ded57ff,

title = "Speech enhancement based on neural networks applied to cochlear implant coding strategies",

abstract = "Traditionally, algorithms that attempt to significantly improve speech intelligibility in noise for cochlear implant (CI) users have met with limited success, particularly in the presence of a fluctuating masker. In the present study, a speech enhancement algorithm integrating an artificial neural network (NN) into CI coding strategies is proposed. The algorithm decomposes the noisy input signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the NN to produce an estimation of which CI channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is then used accordingly to retain a subset of channels for electrical stimulation, as in traditional n-of-m coding strategies. The proposed algorithm was tested with 10 normal-hearing participants listening to CI noise-vocoder simulations against a conventional Wiener filter based enhancement algorithm. Significant improvements in speech intelligibility in stationary and fluctuating noise were found over both unprocessed and Wiener filter processed conditions.",

keywords = "Cochlear implants, machine learning, neural networks, noise reduction, speech enhancement",

author = "Federico Bolner and Tobias Goehring and Jessica Monaghan and {Van Dijk}, Bas and Jan Wouters and Stefan Bleeck",

year = "2016",

month = may,

day = "18",

doi = "10.1109/ICASSP.2016.7472933",

language = "English",

series = "International Conference on Acoustics Speech and Signal Processing ICASSP",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "6520--6524",

booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",

address = "United States",

note = "41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

}

Bolner, F, Goehring, T, Monaghan, J, Van Dijk, B, Wouters, J & Bleeck, S 2016, Speech enhancement based on neural networks applied to cochlear implant coding strategies. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings., 7472933, International Conference on Acoustics Speech and Signal Processing ICASSP, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 6520-6524, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472933

Speech enhancement based on neural networks applied to cochlear implant coding strategies. / Bolner, Federico; Goehring, Tobias; Monaghan, Jessica et al.
2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 6520-6524 7472933 (International Conference on Acoustics Speech and Signal Processing ICASSP).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Speech enhancement based on neural networks applied to cochlear implant coding strategies

AU - Bolner, Federico

AU - Goehring, Tobias

AU - Monaghan, Jessica

AU - Van Dijk, Bas

AU - Wouters, Jan

AU - Bleeck, Stefan

PY - 2016/5/18

Y1 - 2016/5/18

N2 - Traditionally, algorithms that attempt to significantly improve speech intelligibility in noise for cochlear implant (CI) users have met with limited success, particularly in the presence of a fluctuating masker. In the present study, a speech enhancement algorithm integrating an artificial neural network (NN) into CI coding strategies is proposed. The algorithm decomposes the noisy input signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the NN to produce an estimation of which CI channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is then used accordingly to retain a subset of channels for electrical stimulation, as in traditional n-of-m coding strategies. The proposed algorithm was tested with 10 normal-hearing participants listening to CI noise-vocoder simulations against a conventional Wiener filter based enhancement algorithm. Significant improvements in speech intelligibility in stationary and fluctuating noise were found over both unprocessed and Wiener filter processed conditions.

AB - Traditionally, algorithms that attempt to significantly improve speech intelligibility in noise for cochlear implant (CI) users have met with limited success, particularly in the presence of a fluctuating masker. In the present study, a speech enhancement algorithm integrating an artificial neural network (NN) into CI coding strategies is proposed. The algorithm decomposes the noisy input signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the NN to produce an estimation of which CI channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is then used accordingly to retain a subset of channels for electrical stimulation, as in traditional n-of-m coding strategies. The proposed algorithm was tested with 10 normal-hearing participants listening to CI noise-vocoder simulations against a conventional Wiener filter based enhancement algorithm. Significant improvements in speech intelligibility in stationary and fluctuating noise were found over both unprocessed and Wiener filter processed conditions.

KW - Cochlear implants

KW - machine learning

KW - neural networks

KW - noise reduction

KW - speech enhancement

UR - http://www.scopus.com/inward/record.url?scp=84973316242&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472933

DO - 10.1109/ICASSP.2016.7472933

M3 - Conference proceeding contribution

AN - SCOPUS:84973316242

T3 - International Conference on Acoustics Speech and Signal Processing ICASSP

SP - 6520

EP - 6524

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

Y2 - 20 March 2016 through 25 March 2016

ER -

Bolner F, Goehring T, Monaghan J, Van Dijk B, Wouters J, Bleeck S. Speech enhancement based on neural networks applied to cochlear implant coding strategies. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2016. p. 6520-6524. 7472933. (International Conference on Acoustics Speech and Signal Processing ICASSP). doi: 10.1109/ICASSP.2016.7472933

Speech enhancement based on neural networks applied to cochlear implant coding strategies

Abstract

Publication series

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this