Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection

Figure 3

Spectrogram of a 30-second sequence from (a) the A3Novelty Corpus containing a novel siren event (top), (b) the PASCAL CHiME database containing three novel events, such as a siren and two screams, and (c) the PROMETHEUS database containing a novel event composed by an alarm and people screaming together (top). Reconstruction error signal of the related sequence obtained with a BLSTM-DAE (middle). Ground-truth binary novelty signal: novel (0), and not-novel (0) (bottom).

(a)

(b)

(c)