Diffusion MRI is commonly performed using echo-planar imaging (EPI) due ...
In recent studies, self-supervised pre-trained models tend to outperform...
Considering the abundance of unlabeled speech data and the high labeling...
Purpose: To propose a wave-encoded model-based deep learning (wave-MoDL)...
Zero-shot multi-speaker Text-to-Speech (TTS) generates target speaker vo...
In this paper, we explore several new schemes to train a seq2seq model t...
This work explores better adaptation methods to low-resource languages u...
Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...
This paper investigates the impact of word-based RNN language models
(RN...