# Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection Source: [Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:01:59.701Z Authors: Duong Nguyen, Oliver S. Kirsebom, F\\'abio Fraz\\~ao, Ronan Fablet, Stan Matwin Published: 2019-02-13T16:13:52.000Z ## Abstract In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of complex sequences. Because the learned distribution can be calculated explicitly in terms of probability, we can evaluate how likely an observation is then detect low-probability events as novel. The model is robust, highly unsupervised, end-to-end and requires minimum preprocessing, feature engineering or hyperparameter tuning. An experiment on a benchmark dataset shows that our model outperforms the state-of-the-art acoustic novelty detectors. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Acoustic Novelty Detection on PASCAL CHiME (test)](): Acoustic Novelty Detection; PASCAL CHiME (test); F1 Score: 94.1. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()