Abstract
The most accurate approach utilized an estimation of the clean speech power spectral density (PSD) and the noisy speech power across a sliding window of 1280 ms and achieved an total SNR estimation error below 3 dB across a wide variety of background noises and input SNRs
| Original language | English |
|---|---|
| Title of host publication | Proceedings of ICASSP 2017 |
| Publisher | IEEE |
| Publication date | 2017 |
| Pages | 231-235 |
| ISBN (Print) | 978-1-5090-4117-6 |
| DOIs | |
| Publication status | Published - 2017 |
| Event | 42nd IEEE International Conference on Acoustics, Speech and Signal Processing: The internet of signals - Hilton New Orleans Riverside, New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017 Conference number: 42 http://www.ieee-icassp2017.org/ |
Conference
| Conference | 42nd IEEE International Conference on Acoustics, Speech and Signal Processing |
|---|---|
| Number | 42 |
| Location | Hilton New Orleans Riverside |
| Country | United States |
| City | New Orleans |
| Period | 05/03/2017 → 09/03/2017 |
| Internet address |
Keywords
- Signal-to-noise ratio estimation
- Noise power estimation
- Hearing-aid algorithms
Cite this
}
Assessment of broadband SNR estimation for hearing aid applications. / May, Tobias; Kowalewski, Borys; Fereczkowski, Michal; MacDonald, Ewen.
Proceedings of ICASSP 2017. IEEE, 2017. p. 231-235.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
TY - GEN
T1 - Assessment of broadband SNR estimation for hearing aid applications
AU - May, Tobias
AU - Kowalewski, Borys
AU - Fereczkowski, Michal
AU - MacDonald, Ewen
PY - 2017
Y1 - 2017
N2 - An accurate estimation of the broadband input signal-to-noise ratio (SNR) is a prerequisite for many hearing-aid algorithms. An extensive comparison of three SNR estimation algorithms was performed. Moreover, the influence of the duration of the analysis window on the SNR estimation performance was systematically investigated.The most accurate approach utilized an estimation of the clean speech power spectral density (PSD) and the noisy speech power across a sliding window of 1280 ms and achieved an total SNR estimation error below 3 dB across a wide variety of background noises and input SNRs
AB - An accurate estimation of the broadband input signal-to-noise ratio (SNR) is a prerequisite for many hearing-aid algorithms. An extensive comparison of three SNR estimation algorithms was performed. Moreover, the influence of the duration of the analysis window on the SNR estimation performance was systematically investigated.The most accurate approach utilized an estimation of the clean speech power spectral density (PSD) and the noisy speech power across a sliding window of 1280 ms and achieved an total SNR estimation error below 3 dB across a wide variety of background noises and input SNRs
KW - Signal-to-noise ratio estimation
KW - Noise power estimation
KW - Hearing-aid algorithms
U2 - 10.1109/ICASSP.2017.7952152
DO - 10.1109/ICASSP.2017.7952152
M3 - Article in proceedings
SN - 978-1-5090-4117-6
SP - 231
EP - 235
BT - Proceedings of ICASSP 2017
PB - IEEE
ER -