Li-Rong Dai

Publications
Influence

A Regression Approach to Speech Enhancement Based on Deep Neural Networks

Yanchen Xu, J. Du, Li-Rong Dai, Chin-Hui Lee
Computer Science
IEEE/ACM Transactions on Audio, Speech, and…
2015

In contrast to the conventional minimum mean square error (MMSE)-based noise reduction techniques, we propose a supervised method to enhance speech by means of finding a mapping function between noisy and clean speech signals based on deep neural networks (DNNs). Expand

An Experimental Study on Speech Enhancement Based on Deep Neural Networks

Yong Xu, J. Du, Li-Rong Dai, C. Lee
Computer Science
IEEE Signal Processing Letters
2014

This letter presents a regression-based speech enhancement framework using deep neural networks (DNNs) with multiple-layer deep architecture. Expand

The Fixed-Size Ordinally-Forgetting Encoding Method for Neural Network Language Models

S. Zhang, Hui Jiang, Mingbin Xu, Junfeng Hou, Li-Rong Dai
Computer Science
ACL
1 July 2015

In this paper, we propose the new fixedsize ordinally-forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence of words into a fixed-size representation. Expand

WaveNet Vocoder with Limited Training Data for Voice Conversion

L. Liu, Z. Ling, Yuan Jiang, M. Zhou, Li-Rong Dai
Computer Science
INTERSPEECH
2 September 2018

This paper investigates the approaches of building WaveNet vocoder with limited training data for voice conversion (VC). Expand

Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency

S. Zhang, C. Liu, Hui Jiang, Si Wei, Li-Rong Dai, Y. Hu
Computer Science
ArXiv
28 December 2015

We propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback. Expand

Dynamic noise aware training for speech enhancement based on deep neural networks

Yong Xu, J. Du, Li-Rong Dai, C. Lee
Computer Science
INTERSPEECH
2014

We propose three algorithms to address the mismatch problem in deep neural network (DNN) based speech enhancement. Expand

Multiple-target deep learning for LSTM-RNN based speech enhancement

Lei Sun, J. Du, Li-Rong Dai, C. Lee
Computer Science
Hands-free Speech Communications and Microphone…
1 March 2017

In this study, we explore long short-term memory recurrent neural networks (LSTM-RNNs) for speech enhancement. Expand

Robust speech recognition with speech enhanced deep neural networks

J. Du, Q. Wang, Tian Gao, Yong Xu, Li-Rong Dai, C. Lee
Computer Science
INTERSPEECH
2014

We propose a signal pre-processing front-end to enhance speech based on deep neural networks (DNNs) and use the enhanced speech features directly to train hidden Markov models (HMMs) for robust speech recognition. Expand

Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training

L. Chen, Z. Ling, L. Liu, Li-Rong Dai
Computer Science
IEEE/ACM Transactions on Audio, Speech, and…
1 December 2014

This paper presents a new spectral envelope conversion method using deep neural networks (DNNs) to construct a global non-linear mapping relationship between the spectral envelopes of two speakers. Expand

Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition

Shaofei Xue, O. Abdel-Hamid, Hui Jiang, Li-Rong Dai, Qingfeng Liu
Computer Science
IEEE/ACM Transactions on Audio, Speech, and…
1 December 2014

Fast adaptation of deep neural networks (DNN) is an important research topic in deep learning. Expand

Recommended Authors