Auditory Attention Detection (AAD) aims to detect target speaker from br...
The rhythm of synthetic speech is usually too smooth, which causes that ...
In this paper, we propose the multi-perspective information fusion (MPIF...
In this paper, we propose a novel self-distillation method for fake spee...
Previous databases have been designed to further the development of fake...
The existing fake audio detection systems often rely on expert experienc...
Recently, pioneer research works have proposed a large number of acousti...
Audio deepfake detection is an emerging topic, which was included in the...
As an essential element for the diagnosis and rehabilitation of psychiat...
Recurrent neural networks (RNNs) have shown significant improvements in
...
The joint training framework for speech enhancement and recognition meth...
The generative adversarial networks (GANs) have facilitated the developm...
Monaural speech dereverberation is a very challenging task because no sp...
Previous studies demonstrate that word embeddings and part-of-speech (PO...
A person tends to generate dynamic attention towards speech under compli...
In this paper, we propose an end-to-end post-filter method with deep
att...
Multi-channel deep clustering (MDC) has acquired a good performance for
...
Deep clustering (DC) and utterance-level permutation invariant training
...