In this paper, combining features is proposed as a way to enhance the classification accuracy of sounds under noisy environments using the CNN (Convolutional Neural Network) structure. A robust log Mel-filter bank using Wiener filter and PNCCs (Power Normalized Cepstral Coefficients) are extracted to form a 2-dimensional feature that is used as input to the CNN structure. An ebird database is used to classify 43 types of bird species in their natural environment. To evaluate the performance of the combined features under noisy environments, the database is augmented with 3 types of noise under 4 different SNRs (Signal to Noise Ratios) (20 dB, 10 dB, 5 dB, 0 dB). The combined feature is compared to the log Mel-filter bank with and without incorporating the Wiener filter and the PNCCs. The combined feature is shown to outperform the other mentioned features under clean environments with a 1.34 % increase in overall average accuracy. Additionally, the accuracy under noisy environments at the 4 SNR levels is increased by 1.06 % and 0.65 % for shop and schoolyard noise backgrounds, respectively.
Bibliographical noteFunding Information:
This work was funded by the Ministry of Environment supported by the Korea Environmental Industry & Technology Institute's environmental policy-based public technology development project (2017000210001).
© 2019 Acoustical Society of Korea. All rights reserved.
- Acoustic event recognition
- CNN (Convolutional Neural Network)
- Environmental sound classification
- PNCCs (Power Normalized Cepstral Coefficients)
- Weiner filter
ASJC Scopus subject areas
- Acoustics and Ultrasonics
- Applied Mathematics
- Signal Processing
- Speech and Hearing