Most existing keyword spotting research focuses on conditions with sligh...
Recently, speech enhancement (SE) based on deep speech prior has attract...
Zero-shot learning (ZSL) aims to recognize the novel object categories u...
Neural models, in particular the d-vector and x-vector architectures, ha...
Recent studies have shown that frame-level deep speaker features can be
...
Various informative factors mixed in speech signals, leading to great
di...
Recently deep neural networks (DNNs) have been used to learn speaker
fea...
Pure acoustic neural models, particularly the LSTM-RNN model, have shown...
Recurrent neural networks (RNNs) have shown clear superiority in sequenc...