Anomaly Detection in Raw Audio Using Deep Autoregressive Networks
|Title:||Anomaly Detection in Raw Audio Using Deep Autoregressive Networks||Authors:||Rushe, Ellen; MacNamee, Brian||Permanent link:||http://hdl.handle.net/10197/11368||Date:||17-May-2019||Online since:||2020-05-06T08:33:44Z||Abstract:||Anomaly detection involves the recognition of patterns outside of what is considered normal, given a certain set of input data. This presents a unique set of challenges for machine learning, particularly if we assume a semi-supervised scenario in which anomalous patterns are unavailable at training time meaning algorithms must rely on non-anomalous data alone. Anomaly detection in time series adds an additional level of complexity given the contextual nature of anomalies. For time series modelling, autoregressive deep learning architectures such as WaveNet have proven to be powerful generative models, specifically in the field of speech synthesis. In this paper, we propose to extend the use of this type of architecture to anomaly detection in raw audio. In experiments using multiple audio datasets we compare the performance of this approach to a baseline autoencoder model and show superior performance in almost all cases.||Funding Details:||Science Foundation Ireland||metadata.dc.description.othersponsorship:||Insight Research Centre||Type of material:||Conference Publication||Publisher:||IEEE||Copyright (published version):||2019 IEEE||Keywords:||Anomaly detection; Deep learning; Raw audio; WaveNet||DOI:||10.1109/ICASSP.2019.8683414||Language:||en||Status of Item:||Peer reviewed||Is part of:||2019 IEEE International Conference on Acoustics, Speech and Signal Processing: Proceedings||Conference Details:||The 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, Brighton, United Kingdom, 12-17 May 2019||ISBN:||978-1-4799-8131-1|
|Appears in Collections:||Insight Research Collection|
Show full item record
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.