activity
20142023
most citedFew-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes

23 citations · 38 across the 7 of their papers we have counts for

collaborators

7 papers

eess.AS202323 cited

Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes

Yanxiong Li, Wenchang Cao, Wei Xie +2

Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification…

eess.AS2023

Adapting Language-Audio Models as Few-Shot Audio Learners

Jinhua Liang, Xubo Liu, Haohe Liu +4

We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we…

cs.SD20229 cited

Contrastive Audio-Language Learning for Music

Ilaria Manco, Emmanouil Benetos, Elio Quinton +1

As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application…

cs.LG2022

Anomalous behaviour in loss-gradient based interpretability methods

Vinod Subramanian, Siddharth Gururani, Emmanouil Benetos +1

Loss-gradients are used to interpret the decision making process of deep learning models. In this work, we evaluate loss-gradient based attribution methods by occluding parts of th…

cs.SD20161 cited

On-bird Sound Recordings: Automatic Acoustic Recognition of Activities and Contexts

Dan Stowell, Emmanouil Benetos, Lisa F. Gill

We introduce a novel approach to studying animal behaviour and the context in which it occurs, through the use of microphone backpacks carried on the backs of individual free-flyin…

stat.ML20155 cited

An evaluation framework for event detection using a morphological model of acoustic scenes

Mathieu Lagrange, Grégoire Lafay, Mathias Rossignol +2

This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its pote…