Program

Monday 19th November

9:00 Registration &
Coffee/Tea
9:20 Welcome

Mark Plumbley
CVSSP, University of Surrey

9:30 Keynote

Stereophonic autoencoder on bio-transient to enhance biodiversity tracking, and other methods to monitor abyssea

Hervé Glotin

Université de Toulon, CNRS, LIS

Abstract & bio

10:20 Challenge
spotlights

Reports on the 5 tasks of the DCASE 2018 challenge

10:50 Coffee/Tea
11:20 Oral session I

Human and animal sound detection

L01

Acoustic event search with an onomatopoeic query: Measuring distance between onomatopoeic words and sounds
Shota Ikawa, Kunio Kashino

L02

Fast mosquito acoustic detection with field cup recordings: An initial investigation
Yunpeng Li, Ivan Kiskin, Marianne Sinka, Davide Zilli, Henry Chan, Eva Herreros-Moya, Theeraphap Chareonviriyaphap, Rungarun Tisgratog, Kathy Willis, Stephen Roberts

L03

Acoustic bird detection with deep convolutional neural networks
Mario Lasseck

L04

Domain tuning methods for bird audio detection
Sidrah Liaqat, Narjes Bozorg, Neenu Jose, Patrick Conrey, Anthony Tamasi, Michael T. Johnson

12:40 Lunch
13:40 Poster session I

List of posters

15:10 Coffee/Tea
15:40 Oral session II

Learning from weakly-labeled data

L05

Large-scale weakly labeled semi-supervised sound event detection in domestic environments
Romain Serizel, Nicolas Turpault, Hamid Eghbal-Zadeh, Ankit Parag Shah

L06

Sound event detection using weakly labelled semi-supervised data with GCRNNs, VAT and self-adaptive label refinement
Robert Harb, Franz Pernkopf

L07

Iterative knowledge distillation in R-CNNs for weakly-labeled semi-supervised sound event detection
Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer

L08

Data-efficient weakly supervised learning for low-resource audio event detection using deep learning
Veronica Morfi, Dan Stowell

17:00 End of sessions

17:15 - 19:00   Welcome Reception

Tuesday 20th November

9:00 Arrival &
Coffee/Tea
9:20 Keynote

Acoustic condition monitoring for smart city and industry environments

Hanna Lukashevich

Fraunhofer Institute for Digital Media Technology IDMT

Abstract & bio

10:10 Oral session III

Acoustic scene classification

L09

Attention-based convolutional neural networks for acoustic scene classification
Zhao Ren, Qiuqiang Kong, Kun Qian, Mark Plumbley, Björn Schuller

L10

Unsupervised adversarial domain adaptation for acoustic scene classification
Shayan Gharib, Konstantinos Drossos, Emre Cakir, Dmitriy Serdyuk, Tuomas Virtanen

10:50 Coffee/Tea
11:20 Oral session IV

Multi-label audio event classification

L11

A multi-device dataset for urban acoustic scene classification
Annamaria Mesaros, Toni Heittola, Tuomas Virtanen

L12

Training general-purpose audio tagging networks with noisy labels and iterative self-verification
Matthias Dorfer, Gerhard Widmer

L13

Audio tagging system using densely connected convolutional networks
Il-Young Jeong, Hyungui Lim

L14

General-purpose audio tagging by ensembling convolutional neural networks based on multiple features
Kevin Wilkinghoff

12:40 Lunch
13:40 Poster session II

List of posters

15:10 Coffee/Tea
15:40 Panel discussion

TBA

16:40 Closing remarks
17:00 End of workshop