[PDF][PDF] Recent advances in end-to-end automatic speech recognition

J Li - APSIPA Transactions on Signal and Information …, 2022 - nowpublishers.com
Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

Attention-inspired artificial neural networks for speech processing: A systematic review

N Zacarias-Morales, P Pancardo… - Symmetry, 2021 - mdpi.com
Artificial Neural Networks (ANNs) were created inspired by the neural networks in the
human brain and have been widely applied in speech processing. The application areas of …

Phishing websites detection via CNN and multi-head self-attention on imbalanced datasets

X Xiao, W Xiao, D Zhang, B Zhang, G Hu, Q Li… - Computers & Security, 2021 - Elsevier
Phishing websites belong to a social engineering attack where perpetrators fake legitimate
websites to lure people to access so as to illegally acquire user's identity, password, privacy …

Local correlation consistency for knowledge distillation

X Li, J Wu, H Fang, Y Liao, F Wang, C Qian - European Conference on …, 2020 - Springer
Sufficient knowledge extraction from the teacher network plays a critical role in the
knowledge distillation task to improve the performance of the student network. Existing …

Asr is all you need: Cross-modal distillation for lip reading

T Afouras, JS Chung… - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
The goal of this work is to train strong models for visual speech recognition without requiring
human annotated ground truth data. We achieve this by distilling from an Automatic Speech …

Hierarchical transformer-based large-context end-to-end asr with large-context knowledge distillation

R Masumura, N Makishima, M Ihori… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
We present a novel large-context end-to-end automatic speech recognition (E2E-ASR)
model and its effective training method based on knowledge distillation. Common E2E-ASR …

Adaptive knowledge distillation based on entropy

K Kwon, H Na, H Lee, NS Kim - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
Knowledge distillation (KD) approach is widely used in the deep learning field mainly for
model size reduction. KD utilizes soft labels of teacher model, which contain the dark …

Modeling teacher-student techniques in deep neural networks for knowledge distillation

S Abbasi, M Hajabdollahi, N Karimi… - … on Machine Vision …, 2020 - ieeexplore.ieee.org
Knowledge distillation (KD) is a new method for transferring knowledge of a structure under
training to another one. The conventional application of KD is in the form of learning a small …

Mutual-learning sequence-level knowledge distillation for automatic speech recognition

Z Li, Y Ming, L Yang, JH Xue - Neurocomputing, 2021 - Elsevier
Automatic speech recognition (ASR) is a crucial technology for man-machine interaction.
End-to-end models have been studied recently in deep learning for ASR. However, these …

Speech to text adaptation: Towards an efficient cross-modal distillation

WI Cho, D Kwak, JW Yoon, NS Kim - arXiv preprint arXiv:2005.08213, 2020 - arxiv.org
Speech is one of the most effective means of communication and is full of information that
helps the transmission of utterer's thoughts. However, mainly due to the cumbersome …