Session I

Session I

 

A Mixed Supervised Learning Framework for Target Sound Detection
Dongchao Yang, Helin Wang, Wenwu Wang, Yuexian Zou

Poster
P1
Spotlight Talk
9:40

Detect What You Want: Target Sound Detection
Dongchao Yang, Helin Wang, Yuexian Zou, Fan Cui, Yujun Wang

Poster
P2
Spotlight Talk
9:45

Few-shot bioacoustic event detection at the DCASE 2022 challenge*
Ines Nolasco, Dan Stowell, Vincent Lostanlen, Shubhr Singh, Veronica Morfi, Ari Strandburg-Peshkin, Lisa Gill, Emily Grout, Ester Vidana-Villa, Joe Morford, Michael Emmerson, Frants Jensen, Helen Whitehead, Hanna Pamula, Ivan Kiskin

Spotlight Talk
9:50

Leveraging Label Hierarchies for Few-shot Everyday Sound Recognition
Jinhua Liang, Huy Phan, Emmanouil Benetos

Poster
P3
Spotlight Talk
9:55

Polyphonic sound event detection for highly dense birdsong scenes
Alberto Garcia Arroba Parrilla, Dan Stowell

Poster
P4
Spotlight Talk
10:00

DG-MIX: DOMAIN GENERALIZATION FOR ANOMALOUS SOUND DETECTION BASED ON SELF-SUPERVISED LEARNING
Ismail Nejjar, Jean Meunier-Pion, Gaëtan Frusque, Olga Fink

Poster
P5
Spotlight Talk
10:05

Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Using Temporal Modulation Features on Gammatone Auditory Filterbank
Li Kai, Quoc-Huy Nguyen, Yasuji Ota, Masashi Unoki

Poster
P6

Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations
Paul Primus, Gerhard Widmer

Poster
P7
Spotlight Talk
10:10

Additionally, the task posters will be presented in this session.

*These papers have separate spotlight presentations but will be presented in a joint task poster.