article · 2023
SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection
Haihui Chen, Likai Ran, Xixia Sun, Chao Cai
Cited by 19Abstract and details only
Abstract
Anomalous Sound Detection (ASD) aims to identify whether the sound emitted from a machine is anomalous or not. Most advanced methods use 2-D CNNs to extract features of normal sounds from log-mel spectrograms for ASD. However, these methods can not fully exploit temporal information of log-mel spectrograms, resulting in poor performance on some machine types. In this paper, we propose a new framework for ASD named Spectrogram-Wavegram WaveNet (SW-WaveNet), which segments the 2-D log-mel spectrogram into 1-D waveform signals of different frequency bands and combines the representation vector extracted by WaveNet from segmented log-mel spectrograms and Wavegrams, respectively. The proposed framework utilizes WaveNet’s powerful capability of modeling waveform signals to effectively extract temporal information from log-mel spectrograms and Wavegrams. Experiments on the DCASE 2020 Challenge Task 2 dataset show that our framework achieves higher average AUC scores (93.25%) and pAUC scores (87.41%) than the previous works.
Cite this paper
Chen, H., Ran, L., Sun, X., & Cai, C. (2023). SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection. https://doi.org/10.1109/icassp49357.2023.10096742
Chen, Haihui, et al. “SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection.” 2023, pp. 1–5, https://doi.org/10.1109/icassp49357.2023.10096742.
Chen, Haihui, Likai Ran, Xixia Sun, and Chao Cai. 2023. “SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection.” https://doi.org/10.1109/icassp49357.2023.10096742.
Chen, H. et al. (2023) ‘SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection’. Available at: https://doi.org/10.1109/icassp49357.2023.10096742.
@article{chen2023wavenet,
title = {{SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection}},
author = {Chen, Haihui and Ran, Likai and Sun, Xixia and Cai, Chao},
pages = {1--5},
year = {2023},
doi = {10.1109/icassp49357.2023.10096742}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.
Related papers
Estimation of Clean Spectrogram Noisy Value Functions Based on Metropolis Iterative Algorithm.
Mahdi Jalali · Pure and applied physics · 2013
Cited by 0
Using the reassigned spectrogram to obtain a voiceprint
Sean A. Fulop, Kelly Fitz · The Journal of the Acoustical Society of America · 2006
Cited by 0
SW-WAVENET: Learning Representation from Spectrogram and Wavegram Using Wavenet for Anomalous Sound Detection
Haihui Chen, Likai Ran, Xixia Sun et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 2023
Cited by 25
The preliminary application of Gabor spectrogram analysis in speech samples
Jack J. Jiang, Shie Qian, David G. Hanson et al. · The Journal of the Acoustical Society of America · 1993
Cited by 0
Processing noisy line spectrograms as digital pictures
D.G. Nichol · Pattern Recognition · 1977
Cited by 7
Pre-processing spectrogram parameters improve the accuracy of bioacoustic classification using convolutional neural networks
Elly C. Knight, Sergio Poo Hernandez, Erin M. Bayne et al. · Bioacoustics · 2019
Cited by 61Open access
SPECTROGRAM ANALYSIS OF ANIMAL SOUND PRODUCTION
Coen P. H. Elemans, K. Heeck, M. Müller · Bioacoustics · 2008
Cited by 22Open access
Acoustic scene classification based on Mel spectrogram decomposition and model merging
Tao Zhang, Guoqing Feng, Jinhua Liang et al. · Applied Acoustics · 2021
Cited by 77