abstract = {Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large amounts of labeled data are not available. Task4 of the 2018 DCASE challenge presents an event detection task that requires accuracy in both segmentation and recognition of events while providing only weakly labeled training data. Supervised methods can produce accurate event labels but are limited in event segmentation when training data lacks event timestamps. On the other hand, unsupervised methods that model the acoustic properties of the audio can produce accurate event boundaries but are not guided by the characteristics of event classes and sound categories. We present a hybrid approach that combines an acoustic-driven event boundary detection and a supervised label inference using a deep neural network. This framework leverages benefits of both unsupervised and supervised methodologies and takes advantage of large amounts of unlabeled data, making it ideal for large-scale weakly la-beled event detection. Compared to a baseline system, the proposed approach delivers a 15{\%} absolute improvement in F-score, demonstrating the benefits of the hybrid bottom-up, top-down approach.},
author = {Kothinti, Sandeep and Imoto, Keisuke and Chakrabarty, Debmalya and Sell, Gregory and Watanabe, Shinji and Elhilali, Mounya},
booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP.2019.8682772},
isbn = {978-1-4799-8131-1},
pages = {36--40},
publisher = {IEEE},
title = {{Joint Acoustic and Class Inference for Weakly Supervised Sound Event Detection}},
url = {https://ieeexplore.ieee.org/document/8682772/},
year = {2019}