Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tao Qin

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior


Jun 11, 2021
Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu, Qi Meng, Tao Qin, Wei Chen, Sungroh Yoon, Tie-Yan Liu

* 16 pages, 5 figures, 7 tables. Audio samples: https://speechresearch.github.io/priorgrad/ 

  Access Paper or Ask Questions

MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training


Jun 10, 2021
Mingliang Zeng, Xu Tan, Rui Wang, Zeqian Ju, Tao Qin, Tie-Yan Liu

* Accepted by ACL 2021 Findings 

  Access Paper or Ask Questions

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition


Jun 03, 2021
Yichong Leng, Xu Tan, Linchen Zhu, Jin Xu, Renqian Luo, Linquan Liu, Tao Qin, Xiang-Yang Li, Ed Lin, Tie-Yan Liu


  Access Paper or Ask Questions

NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search


May 30, 2021
Jin Xu, Xu Tan, Renqian Luo, Kaitao Song, Jian Li, Tao Qin, Tie-Yan Liu

* Accepted by KDD 2021 

  Access Paper or Ask Questions

Learning Structures for Deep Neural Networks


May 27, 2021
Jinhui Yuan, Fei Pan, Chunting Zhou, Tao Qin, Tie-Yan Liu


  Access Paper or Ask Questions

Exploiting Adapters for Cross-lingual Low-resource Speech Recognition


May 18, 2021
Wenxin Hou, Han Zhu, Yidong Wang, Jindong Wang, Tao Qin, Renjun Xu, Takahiro Shinozaki

* Technical report 

  Access Paper or Ask Questions

AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data


Apr 20, 2021
Yuzi Yan, Xu Tan, Bohan Li, Tao Qin, Sheng Zhao, Yuan Shen, Tie-Yan Liu

* Accepted by ICASSP 2021 

  Access Paper or Ask Questions

Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching


Apr 16, 2021
Wenxin Hou, Jindong Wang, Xu Tan, Tao Qin, Takahiro Shinozaki

* submitted to INTERSPEECH 2021; code available at https://github.com/jindongwang/transferlearning/tree/master/code/ASR/CMatch 

  Access Paper or Ask Questions

UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost


Apr 11, 2021
Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu

* Accepted by NAACL 2021 

  Access Paper or Ask Questions

Generalizing to Unseen Domains: A Survey on Domain Generalization


Mar 10, 2021
Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin

* Technical report 

  Access Paper or Ask Questions

IOT: Instance-wise Layer Reordering for Transformer Structures


Mar 05, 2021
Jinhua Zhu, Lijun Wu, Yingce Xia, Shufang Xie, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

* Accepted at ICLR-2021 

  Access Paper or Ask Questions

Learning Invariant Representations across Domains and Tasks


Mar 03, 2021
Jindong Wang, Wenjie Feng, Chang Liu, Chaohui Yu, Mingxuan Du, Renjun Xu, Tao Qin, Tie-Yan Liu

* Technical report, 12 pages 

  Access Paper or Ask Questions

AdaSpeech: Adaptive Text to Speech for Custom Voice


Mar 01, 2021
Mingjian Chen, Xu Tan, Bohan Li, Yanqing Liu, Tao Qin, Sheng Zhao, Tie-Yan Liu

* Accepted by ICLR 2021 

  Access Paper or Ask Questions

MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network


Feb 27, 2021
Yichong Leng, Xu Tan, Sheng Zhao, Frank Soong, Xiang-Yang Li, Tao Qin

* Accepted by ICASSP 2021 

  Access Paper or Ask Questions

MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition


Feb 25, 2021
Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu

* To appear at ICASSP 2021 

  Access Paper or Ask Questions

Return-Based Contrastive Representation Learning for Reinforcement Learning


Feb 22, 2021
Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu

* ICLR 2021 

  Access Paper or Ask Questions

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search


Feb 08, 2021
Renqian Luo, Xu Tan, Rui Wang, Tao Qin, Jinzhu Li, Sheng Zhao, Enhong Chen, Tie-Yan Liu

* Accepted to ICASSP 21 

  Access Paper or Ask Questions

Image-to-Image Translation: Methods and Applications


Jan 21, 2021
Yingxue Pang, Jianxin Lin, Tao Qin, Zhibo Chen

* 19 pages, 17 figures 

  Access Paper or Ask Questions

SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint


Dec 09, 2020
Zhonghao Sheng, Kaitao Song, Xu Tan, Yi Ren, Wei Ye, Shikun Zhang, Tao Qin


  Access Paper or Ask Questions

Latent Causal Invariant Model


Nov 04, 2020
Xinwei Sun, Botong Wu, Chang Liu, Xiangyu Zheng, Wei Chen, Tao Qin, Tie-yan Liu


  Access Paper or Ask Questions

Learning Causal Semantic Representation for Out-of-Distribution Prediction


Nov 03, 2020
Chang Liu, Xinwei Sun, Jindong Wang, Tao Li, Tao Qin, Wei Chen, Tie-Yan Liu


  Access Paper or Ask Questions

Meta-Learning for Low-Resource Unsupervised Neural MachineTranslation


Oct 18, 2020
Yunwon Tae, Cheonbok Park, Taehee Kim, Soyoung Yang, Mohammad Azam Khan, Eunjeong Park, Tao Qin, Jaegul Choo

* 10 pages, 4 figures 

  Access Paper or Ask Questions

Masked Contrastive Representation Learning for Reinforcement Learning


Oct 15, 2020
Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng, Wengang Zhou, Tao Qin, Houqiang Li

* Work in progress 

  Access Paper or Ask Questions

Towards Interpretable Reasoning over Paragraph Effects in Situation


Oct 03, 2020
Mucheng Ren, Xiubo Geng, Tao Qin, Heyan Huang, Daxin Jiang

* 14 pages. Accepted as EMNLP2020 Long paper 

  Access Paper or Ask Questions

Knowledge-Aware Procedural Text Understanding with Multi-Stage Training


Sep 28, 2020
Zhihan Zhang, Xiubo Geng, Tao Qin, Yunfang Wu, Daxin Jiang


  Access Paper or Ask Questions

HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis


Sep 03, 2020
Jiawei Chen, Xu Tan, Jian Luan, Tao Qin, Tie-Yan Liu


  Access Paper or Ask Questions