Imagine standing on a street corner in the city. With your eyes closed you can hear and
recognize a succession of sounds: cars passing by, people speaking, their footsteps when …

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-
specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and …

As sound event classification moves towards larger datasets, issues of label noise become
inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but …

We investigate the problem of acoustic scene classification, using a deep residual network
applied to log-mel spectrograms complemented by log-mel deltas and delta-deltas. We …

Convolutional Neural Networks (CNNs) have had great success in many machine vision as
well as machine audition tasks. Many image recognition network architectures have …

In this paper, we present the system description of the joint efforts of Brno University of
Technology (BUT) and Omilia--Conversational Intelligence for the ASVSpoof2019 Spoofing …

Acoustic scene classification and related tasks have been dominated by Convolutional
Neural Networks (CNNs). Top-performing CNNs use mainly audio spectograms as input and …

In this article we explore how the different semantics of spectrograms' time and frequency
axes can be exploited for musical tempo and key estimation using Convolutional Neural …

Deep neural networks are particularly useful to learn relevant representations from data.
Recent studies have demonstrated the potential of unsupervised representation learning for …

We present CP-JKU submission to MediaEval 2019; a Receptive Field-(RF)-regularized and
Frequency-Aware CNN approach for tagging music with emotion/mood labels. We perform …