Format

Send to

Choose Destination
Comput Intell Neurosci. 2017;2017:4694860. doi: 10.1155/2017/4694860. Epub 2017 Jan 15.

Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection.

Author information

1
Machine Intelligence & Signal Processing Group, Technische Universität München, Munich, Germany; audEERING GmbH, Gilching, Germany; Chair of Complex & Intelligent Systems, University of Passau, Passau, Germany.
2
A3LAB, Department of Information Engineering, Università Politecnica delle Marche, Ancona, Italy.
3
audEERING GmbH, Gilching, Germany; Chair of Complex & Intelligent Systems, University of Passau, Passau, Germany; Department of Computing, Imperial College London, London, UK.

Abstract

In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F-measure over the three databases.

PMID:
28182121
PMCID:
PMC5274684
DOI:
10.1155/2017/4694860
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Hindawi Publishing Corporation Icon for PubMed Central
Loading ...
Support Center