Scene-dependent Anomalous Acoustic-event Detection Based on Conditional Wavenet and I-vector
Tatsuya Komatsu, Tomoki Hayashiy, Reishi Kondo, Tomoki Todaz, Kazuya Takeday · 2019
This paper proposes a scene-dependent anomalous acoustic-event detection based on conditional WaveNet and i-vector. The WaveNet builds normal acoustic event models by exhaustive learning of time-domain signals in the public space to provide scene-independent anomaly detection. I-vectors are used as additional features to describe acoustic scenes, where the input signals are observed, to complement the WaveNet. The proposed method can detect anomalous acoustic-events in environments whose acoustic scenes vary depending on time, location, and surrounding environment. Evaluations with data recorded from the real environment demonstrate that the proposed method achieved as much as 15 pt higher F-measure than LSTM and AE. The difference in F-measure by the WaveNet with and without i-vector turned out to be 1.5 pt.