Abstract
The noise reduction (NR) approach is a critical component for enabling hearing aid (HA) users to attain improved speech perception capabilities and to reduce the listening effort under noisy conditions. More specifically, the NR can improve the output signal-to-noise ratio (SNR) level to enhance the speech intelligibility and sound quality for individuals with hearing loss. Recently, a discriminative post-filter (DPF) approach has been developed and the preliminary results indicate that the DPF can further improve the output SNR performance. It is important to specify suitable parameters for the DPF; however, it remains unknown how to set these parameters properly. Therefore, this study mainly focuses on the genetic algorithm (GA) to investigate these parameters of the DPF to further enhance the output SNR performance for HA users. The results of the objective evaluations show that under noisy conditions, the parameters of the DPF investigated by the GA algorithm can maintain the sound quality and yield higher SNR performance as compared to the NR approach used solely. More specifically, the proposed method can enhance the output SNR over the NR approach applied singly by 5.31 dB and 4.05 dB at SNR conditions of 0 dB and 5 dB, respectively. It implies that the proposed approach can help HA users to reduce the listening effort and to hear well even in noisy conditions.
| Original language | English |
|---|---|
| Title of host publication | XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 |
| Editors | Efthyvoulos Kyriacou, Stelios Christofides, Constantinos S. Pattichis |
| Publisher | Springer Verlag |
| Pages | 209-214 |
| Number of pages | 6 |
| Volume | 57 |
| ISBN (Print) | 9783319327013 |
| DOIs | |
| Publication status | Published - 2016 Jan 1 |
| Event | 14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 - Paphos, Cyprus Duration: 2016 Mar 31 → 2016 Apr 2 |
Other
| Other | 14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 |
|---|---|
| Country | Cyprus |
| City | Paphos |
| Period | 16/3/31 → 16/4/2 |
Fingerprint
Keywords
- Discriminative post filter
- Generalized maximum a posteriori spectral amplitude
- Genetic algorithm
- Hearing aids
- Noise reduction
ASJC Scopus subject areas
- Bioengineering
- Biomedical Engineering
Cite this
Improving the performance of noise reduction in hearing aids based on the genetic algorithm. / Lai, Ying Hui; Chen, Chien Hsun; Tang, Shih Tsang; Yeh, Zong-Mu; Tsao, Yu.
XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016. ed. / Efthyvoulos Kyriacou; Stelios Christofides; Constantinos S. Pattichis. Vol. 57 Springer Verlag, 2016. p. 209-214.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Improving the performance of noise reduction in hearing aids based on the genetic algorithm
AU - Lai, Ying Hui
AU - Chen, Chien Hsun
AU - Tang, Shih Tsang
AU - Yeh, Zong-Mu
AU - Tsao, Yu
PY - 2016/1/1
Y1 - 2016/1/1
N2 - The noise reduction (NR) approach is a critical component for enabling hearing aid (HA) users to attain improved speech perception capabilities and to reduce the listening effort under noisy conditions. More specifically, the NR can improve the output signal-to-noise ratio (SNR) level to enhance the speech intelligibility and sound quality for individuals with hearing loss. Recently, a discriminative post-filter (DPF) approach has been developed and the preliminary results indicate that the DPF can further improve the output SNR performance. It is important to specify suitable parameters for the DPF; however, it remains unknown how to set these parameters properly. Therefore, this study mainly focuses on the genetic algorithm (GA) to investigate these parameters of the DPF to further enhance the output SNR performance for HA users. The results of the objective evaluations show that under noisy conditions, the parameters of the DPF investigated by the GA algorithm can maintain the sound quality and yield higher SNR performance as compared to the NR approach used solely. More specifically, the proposed method can enhance the output SNR over the NR approach applied singly by 5.31 dB and 4.05 dB at SNR conditions of 0 dB and 5 dB, respectively. It implies that the proposed approach can help HA users to reduce the listening effort and to hear well even in noisy conditions.
AB - The noise reduction (NR) approach is a critical component for enabling hearing aid (HA) users to attain improved speech perception capabilities and to reduce the listening effort under noisy conditions. More specifically, the NR can improve the output signal-to-noise ratio (SNR) level to enhance the speech intelligibility and sound quality for individuals with hearing loss. Recently, a discriminative post-filter (DPF) approach has been developed and the preliminary results indicate that the DPF can further improve the output SNR performance. It is important to specify suitable parameters for the DPF; however, it remains unknown how to set these parameters properly. Therefore, this study mainly focuses on the genetic algorithm (GA) to investigate these parameters of the DPF to further enhance the output SNR performance for HA users. The results of the objective evaluations show that under noisy conditions, the parameters of the DPF investigated by the GA algorithm can maintain the sound quality and yield higher SNR performance as compared to the NR approach used solely. More specifically, the proposed method can enhance the output SNR over the NR approach applied singly by 5.31 dB and 4.05 dB at SNR conditions of 0 dB and 5 dB, respectively. It implies that the proposed approach can help HA users to reduce the listening effort and to hear well even in noisy conditions.
KW - Discriminative post filter
KW - Generalized maximum a posteriori spectral amplitude
KW - Genetic algorithm
KW - Hearing aids
KW - Noise reduction
UR - http://www.scopus.com/inward/record.url?scp=84968538395&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84968538395&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-32703-7_43
DO - 10.1007/978-3-319-32703-7_43
M3 - Conference contribution
AN - SCOPUS:84968538395
SN - 9783319327013
VL - 57
SP - 209
EP - 214
BT - XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016
A2 - Kyriacou, Efthyvoulos
A2 - Christofides, Stelios
A2 - Pattichis, Constantinos S.
PB - Springer Verlag
ER -