Name
Title | ||
|---|---|---|
Batch Uniformization for Minimizing Maximum Anomaly Score of Dnn-Based Anomaly Detection in Sounds |
Abstract | ||
|---|---|---|
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One problem with this approach is that the anomaly score of rare-normal sounds becomes higher than that of frequent-normal sounds, because the sample mean is strongly affected by frequent- normal samples, resulting in preferentially decreasing the anomaly score of frequent-normal samples. To decrease anomaly scores for both frequent- and rare-normal sounds, we propose batch uniformization, a training method for unsupervised-ADS for minimizing a weighted average of the anomaly score on each sample in a mini-batch. We used the reciprocal of the probabilistic density of each sample as the weight, more intuitively, a large weight is given for rare-normal sounds. Such a weight works to give a constant anomaly score for both frequent- and rare-normal sounds. Since the probabilistic density is unknown, we estimate it by using the kernel density estimation on each training mini-batch. Verification- and objective-experiments show that the proposed batch uniformization improves the performance of unsupervised-ADS. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/WASPAA.2019.8937183 | 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) |
Keywords | Field | DocType |
Anomaly detection in sounds,uniform distribution,kernel density estimation and deep learning | Reciprocal,Anomaly detection,Uniformization (set theory),Autoencoder,Pattern recognition,Sample mean and sample covariance,Computer science,Uniform distribution (continuous),Artificial intelligence,Acoustics,Probabilistic logic,Kernel density estimation | Conference |
ISSN | ISBN | Citations |
1931-1168 | 978-1-7281-1124-7 | 2 |
PageRank | References | Authors |
0.43 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Koizumi Yuma | 1 | 41 | 11.75 |
| Shoichiro Saito | 2 | 4 | 0.85 |
| Masataka Yamaguchi | 3 | 3 | 0.77 |
| Shin Murata | 4 | 3 | 1.80 |
| Harada Noboru | 5 | 67 | 25.07 |