Batch Uniformization for Minimizing Maximum Anomaly Score of Dnn-Based Anomaly Detection in Sounds
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6-10
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Audio Surveillance of Roads: A System for Detecting Anomalous SoundsIEEE Transactions on Intelligent Transportation Systems, 2015
- Non-linear prediction with LSTM recurrent neural networks for acoustic novelty detection2015
- Assessing the performance of a semi‐automated acoustic monitoring system for primatesMethods in Ecology and Evolution, 2015
- A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks2015
- Probabilistic Novelty Detection for Acoustic Surveillance Under Real-World ConditionsIEEE Transactions on Multimedia, 2011
- Anomaly detectionACM Computing Surveys, 2009
- An overview of anomaly detection techniques: Existing solutions and latest technological trendsComputer Networks, 2007
- Inspection of Visible and Invisible Features of Objects with Image and Sound Signal Processing2006
- Events Detection for an Audio-Based Surveillance System2005
- A Survey of Outlier Detection MethodologiesArtificial Intelligence Review, 2004