most citedKnowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization

1 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2019

Incremental Learning from Scratch for Task-Oriented Dialogue Systems

Weikang Wang, Jiajun Zhang, Qian Li +3

Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands a…

cs.CL20191 cited

Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization

Yangyang Shi, Mei-Yuh Hwang, Xin Lei +1

Recurrent Neural Networks (RNNs) have dominated language modeling because of their superior performance over traditional N-gram based models. In many applications, a large Recurren…

cs.CL20191 cited

End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model

Yangyang Shi, Mei-Yuh Hwang, Xin Lei

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficien…

cs.CL2018

Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language

He Bai, Yu Zhou, Jiajun Zhang +3

To deploy a spoken language understanding (SLU) model to a new language, language transferring is desired to avoid the trouble of acquiring and labeling a new big SLU corpus. Trans…

cs.CL2018

Training Augmentation with Adversarial Examples for Robust Speech Recognition

Sining Sun, Ching-Feng Yeh, Mari Ostendorf +2

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast…

cs.CL2018

Domain Adversarial Training for Accented Speech Recognition

Sining Sun, Ching-Feng Yeh, Mei-Yuh Hwang +2

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source…