Search
Now showing items 1-6 of 6
Towards joint sound scene and polyphonic sound event recognition
(International Speech Communication Association (ISCA), 2019-09-15)
Acoustic Scene Classification (ASC) and Sound Event Detection (SED) are two separate tasks in the field of computational sound scene analysis. In this work, we present a new dataset with both sound scene and sound event ...
Polyphonic sound event and sound activity detection: a multi-task approach
(IEEE, 2019-10-20)
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 ...
An evaluation of data augmentation methods for sound scene geotagging
(International Speech and Communication Association (ISCA), 2021-08-30)
Sound scene geotagging is a new topic of research which has evolved from acoustic scene classification. It is motivated by the idea of audio surveillance. Not content with only describing a scene in a recording, a machine ...
Prototypical Networks for Domain Adaptation in Acoustic Scene Classification
(IEEE, 2021-06-06)
Acoustic Scene Classification (ASC) refers to the task of assigning a semantic label to an audio stream that characterizes the environment in which it was recorded. In recent times, Deep Neural Networks (DNNs) have emerged ...
Onsets, activity, and events: a multi-task approach for polyphonic sound event modelling
(2019-10-25)
State of the art polyphonic sound event detection (SED) systems function as frame-level multi-label classification models. In the context of dynamic polyphony levels at each frame, sound events interfere with each other ...
Memory Controlled Sequential Self Attention for Sound Recognition
(International Speech and Communication Association (ISCA), 2020-10-25)
In this paper we investigate the importance of the extent of memory in sequential self attention for sound recognition. We propose to use a memory controlled sequential self attention mechanism on top of a convolutional ...