A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition

May 20, 2020
Dongwei Jiang, Wubo Li, Ruixiong Zhang, Miao Cao, Ne Luo, Yang Han, Wei Zou, Xiangang Li


  Access Model/Code and Paper
Adversarial Multi-Binary Neural Network for Multi-class Classification

Mar 25, 2020
Haiyang Xu, Junwen Chen, Kun Han, Xiangang Li


  Access Model/Code and Paper
Learning Syntactic and Dynamic Selective Encoding for Document Summarization

Mar 25, 2020
Haiyang Xu, Yahao He, Kun Han, Junwen Chen, Xiangang Li

* IJCNN 2019 

  Access Model/Code and Paper
Selective Attention Encoders by Syntactic Graph Convolutional Networks for Document Summarization

Mar 18, 2020
Haiyang Xu, Yun Wang, Kun Han, Baochang Ma, Junwen Chen, Xiangang Li

* ICASSP 2020 

  Access Model/Code and Paper
Improving Transformer-based Speech Recognition Using Unsupervised Pre-training

Oct 31, 2019
Dongwei Jiang, Xiaoning Lei, Wubo Li, Ne Luo, Yuxuan Hu, Wei Zou, Xiangang Li

* Submitted to ICASSP 2020 

  Access Model/Code and Paper
TCT: A Cross-supervised Learning Method for Multimodal Sequence Representation

Oct 23, 2019
Wubo Li, Wei Zou, Xiangang Li

* submitted to ICASSP 2020 

  Access Model/Code and Paper
Cross-task pre-training for acoustic scene classification

Oct 22, 2019
Ruixiong Zhang, Wei Zou, Xiangang Li

* submitted to ICASSP2020 

  Access Model/Code and Paper
Learning Alignment for Multimodal Emotion Recognition from Speech

Sep 06, 2019
Haiyang Xu, Hui Zhang, Kun Han, Yun Wang, Yiping Peng, Xiangang Li

* InterSpeech 2019 

  Access Model/Code and Paper
DELTA: A DEep learning based Language Technology plAtform

Aug 02, 2019
Kun Han, Junwen Chen, Hui Zhang, Haiyang Xu, Yiping Peng, Yun Wang, Ning Ding, Hui Deng, Yonghu Gao, Tingwei Guo, Yi Zhang, Yahao He, Baochang Ma, Yulong Zhou, Kangli Zhang, Chao Liu, Ying Lyu, Chenxi Wang, Cheng Gong, Yunbo Wang, Wei Zou, Hui Song, Xiangang Li

* White paper for an open source library: https://github.com/didi/delta. 13 pages, 3 figures 

  Access Model/Code and Paper
Towards End-to-End Code-Switching Speech Recognition

Nov 01, 2018
Ne Luo, Dongwei Jiang, Shuaijiang Zhao, Caixia Gong, Wei Zou, Xiangang Li

* 5 pages, submitted to ICASSP 2019 

  Access Model/Code and Paper
A comparable study of modeling units for end-to-end Mandarin speech recognition

May 14, 2018
Wei Zou, Dongwei Jiang, Shuaijiang Zhao, Xiangang Li

* 5 pages 

  Access Model/Code and Paper
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling

Aug 12, 2017
Hairong Liu, Zhenyao Zhu, Xiangang Li, Sanjeev Satheesh

* Published at ICML 2017 

  Access Model/Code and Paper
Deep Speaker: an End-to-End Neural Speaker Embedding System

May 05, 2017
Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, Zhenyao Zhu


  Access Model/Code and Paper
Long Short-Term Memory based Convolutional Recurrent Neural Networks for Large Vocabulary Speech Recognition

Oct 11, 2016
Xiangang Li, Xihong Wu

* Published in INTERSPEECH 2015, September 6-10, 2015, Dresden, Germany 

  Access Model/Code and Paper
Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition

May 11, 2015
Xiangang Li, Xihong Wu

* submitted to ICASSP 2015 which does not perform blind reviews 

  Access Model/Code and Paper