Zero-shot cross-domain slot filling aims to transfer knowledge from the
...
Most existing slot filling models tend to memorize inherent patterns of
...
Multi-domain text classification can automatically classify texts in var...
In this paper, we introduce the task of language-queried audio source
se...
Acoustic scene classification (ASC) aims to classify an audio clip based...
Audio captioning aims at using natural language to describe the content ...
Automated audio captioning aims to use natural language to describe the
...
Deep generative models have recently achieved impressive performance in
...