The performance of speaker verification degrades significantly in advers...
The success of adversarial attacks to speaker recognition is mainly in
w...
Recently, the unified streaming and non-streaming two-pass (U2/U2++)
end...
Although the security of automatic speaker verification (ASV) is serious...
Adversarial attack approaches to speaker identification either need high...
Keyword spotting (KWS) enables speech-based user interaction and gradual...
Deep learning based speaker localization has shown its advantage in
reve...
Conventional sound source localization methods are mostly based on a sin...
Unsupervised domain adaptation (UDA) transfers knowledge from a label-ri...
Ad-hoc microphone arrays has recieved attention, in which the number and...
Transformer-based end-to-end speech recognition models have received
con...
Deep neural networks provide effective solutions to small-footprint keyw...
Multilayer bootstrap network (MBN), which is a recent simple unsupervise...
Recently, ad-hoc microphone array has been widely studied. Unlike tradit...
Recently, conformer-based end-to-end automatic speech recognition, which...
Self-attention (SA), which encodes vector sequences according to their
p...
Recently, speech recognition with ad-hoc microphone arrays has received ...
Nonnegative matrix factorization (NMF) based topic modeling methods do n...
Multichannel blind source separation aims to recover the latent sources ...
Recently, the research on ad-hoc microphone arrays with deep learning ha...
The design of acoustic features is important for speech separation. It c...
Robust voice activity detection (VAD) is a challenging task in low
signa...
Recently, several studies reported that dot-product selfattention (SA) m...
One difficult problem of keyword spotting is how to miniaturize its memo...
The study of unsupervised learning can be generally divided into two
cat...
Deep embedding based text-independent speaker verification has demonstra...
Topic modeling is widely studied for the dimension reduction and analysi...
Recently, deep clustering (DPCL) based speaker-independent speech separa...
Deep learning based speech enhancement methods face two problems. First,...
This paper presents a linear regression based back-end for speaker
verif...
Recently, multilayer bootstrap network (MBN) has demonstrated promising
...
In (zhang2014nonlinear,zhang2014nonlinear2), we have viewed machine
lear...
Multilayer bootstrap network builds a gradually narrowed multilayer nonl...
Unsupervised deep learning is one of the most powerful representation
le...
Recently, the deep-belief-networks (DBN) based voice activity detection ...