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