@conference{a7008ac39e7e4dca87b5b55b3b4d28f5,
author = "Guangpu Huang and Toni Heittola and Tuomas Virtanen",
abstract = "To detect the class, and start and end times of sound events in real world recordings is a challenging task. Current computer systems often show relatively high frame-wise accuracy but low event-wise accuracy. In this paper, we attempted to merge the gap by explicitly including sequential information to improve the performance of a state-of-the-art polyphonic sound event detection system. We propose to 1) use delayed predictions of event activities as additional input features that are fed back to the neural network; 2) build N-grams to model the co-occurrence probabilities of different events; 3) use se-quentialloss to train neural networks. Our experiments on a corpus of real world recordings show that the N-grams could smooth the spiky output of a state-of-the-art neural network system, and improve both the frame-wise and the event-wise metrics.",
booktitle = "16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018",
day = "2",
doi = "10.1109/IWAENC.2018.8521367",
keywords = "Language modelling; Polyphonic sound event detection; Sequential information",
month = "11",
pages = "291--295",
publisher = "IEEE",
title = "{U}sing sequential information in polyphonic sound event detection",
year = "2018",
}