Polyphonic Sound Event Detection (SED) in real-world recordings is a challenging task because of the dynamic polyphony level, intensity, and duration of sound events. Current polyphonic SED systems fail to model the temporal structure of sound events explicitly and instead attempt to look at which sound events are present at each audio frame. Consequently, the event-wise detection performance is much lower than the segment-wise detection performance. In this work, we propose a joint model approach to improve the temporal localization of sound events using a multi-task learning setup. The first task predicts which sound events are present at each time frame; we call this branch 'Sound Event Detection (SED) model', while the second task predicts if a sound event is present or not at each frame; we call this branch 'Sound Activity Detection (SAD) model'. We verify the proposed joint model by comparing it with a separate implementation of both tasks aggregated together from individual task predictions. Our experiments on the URBAN-SED dataset show that the proposed joint model can alleviate False Positive (FP) and False Negative (FN) errors and improve both the segment-wise and the event-wise metrics.

An adversarial attack is an algorithm that perturbs the input of a machine learning model in an intelligent way in order to change the output of the model. An important property of adversarial attacks is transferability. According to this property, it is possible to generate adversarial perturbations on one model and apply it the input to fool the output of a different model. Our work focuses on studying the transferability of adversarial attacks in sound event classification. We are able to demonstrate differences in transferability properties from those observed in computer vision. We show that dataset normalization techniques such as z-score normalization does not affect the transferability of adversarial attacks and we show that techniques such as knowledge distillation do not increase the transferability of attacks.

Bird activity detection (BAD) deals with the task of predicting the presence or absence of bird vocalizations in a given audio recording. In this paper, we propose an all-convolutional neural network (all-conv net) for bird activity detection. All the layers of this network including pooling and dense layers are implemented using convolution operations. The pooling operation implemented by convolution is termed as learned pooling. This learned pooling takes into account the inter feature-map correlations which are ignored in traditional max-pooling. This helps in learning a pooling function which aggregates the complementary information in various feature maps, leading to better bird activity detection. Experimental observations confirm this hypothesis. The performance of the proposed all-conv net is evaluated on the BAD Challenge 2017 dataset. The proposed all-conv net achieves state-of-art performance with a simple architecture and does not employ any data pre-processing or data augmentation techniques.

No abstract

No abstract