activity
20132023
most citedFew-shot bioacoustic event detection at the DCASE 2023 challenge

6 citations · 12 across the 6 of their papers we have counts for

collaborators
Showing 2018Show all

8 papers · 1 filter

eess.AS2018

Sparse Gaussian Process Audio Source Separation Using Spectrum Priors in the Time-Domain

Pablo A. Alvarado, Mauricio A. Álvarez, Dan Stowell

Gaussian process (GP) audio source separation is a time-domain approach that circumvents the inherent phase approximation issue of spectrogram based methods. Furthermore, through i…

cs.SD2018

NIPS4Bplus: a richly annotated birdsong audio dataset

Veronica Morfi, Yves Bas, Hanna Pamuła +2

Recent advances in birdsong detection and classification have approached a limit due to the lack of fully annotated recordings. In this paper, we present NIPS4Bplus, the first rich…

eess.SP2018

Unifying Probabilistic Models for Time-Frequency Analysis

William J. Wilkinson, Michael Riis Andersen, Joshua D. Reiss +2

In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts. They adapt to the incoming signal, quantify uncertaint…

cs.SD2018

Automatic acoustic identification of individual animals: Improving generalisation across species and recording conditions

Dan Stowell, Tereza Petrusková, Martin Šálek +1

Many animals emit vocal sounds which, independently from the sounds' function, embed some individually-distinctive signature. Thus the automatic recognition of individuals by sound…

cs.LG2018

Deep Learning for Audio Transcription on Low-Resource Datasets

Veronica Morfi, Dan Stowell

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events presen…

cs.SD2018

Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning

Veronica Morfi, Dan Stowell

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio…