Real-world complex acoustic environments especially the ones with a low
...
It is difficult for an end-to-end (E2E) ASR system to recognize words su...
Customized keyword spotting (KWS) has great potential to be deployed on ...
Leveraging context information is an intuitive idea to improve performan...
Conversational automatic speech recognition (ASR) is a task to recognize...
Recently self-supervised learning has emerged as an effective approach t...
End-to-end models are favored in automatic speech recognition (ASR) beca...
This paper proposes an extremely lightweight phone-based transducer mode...
The attention mechanism of the Listen, Attend and Spell (LAS) model requ...
In this paper, we propose a domain adversarial training (DAT) algorithm ...
This paper explores the use of adversarial examples in training speech
r...
We investigate the use of generative adversarial networks (GANs) in spee...