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 Lei Xie

Lei Xie

IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion


Jan 02, 2022
Wendong Gan, Bolong Wen, Ying Yan, Haitao Chen, Zhichao Wang, Hongqiang Du, Lei Xie, Kaixuan Guo, Hai Li

Figure 1 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 2 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 3 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Figure 4 for IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Perceptive Mobile Network with Distributed Target Monitoring Terminals: Leaking Communication Energy for Sensing


Dec 29, 2021
Lei Xie, Peilan Wang, S. H. Song, Khaled B. Letaief

Figure 1 for Perceptive Mobile Network with Distributed Target Monitoring Terminals: Leaking Communication Energy for Sensing
Figure 2 for Perceptive Mobile Network with Distributed Target Monitoring Terminals: Leaking Communication Energy for Sensing
Figure 3 for Perceptive Mobile Network with Distributed Target Monitoring Terminals: Leaking Communication Energy for Sensing
Figure 4 for Perceptive Mobile Network with Distributed Target Monitoring Terminals: Leaking Communication Energy for Sensing
* This paper has been submitted to the IEEE for possible publication 
  Access Paper or Ask Questions

Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios


Dec 23, 2021
Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang, Lei Xie, Guoqiao Yu, Guanglu Wan

Figure 1 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 2 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 3 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 4 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
* submitted to icassp2022 
  Access Paper or Ask Questions

A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements


Dec 04, 2021
Ziqiang Wang, Yimao Sun, Qun Wan, Lei Xie, Ning Liu

Figure 1 for A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements
Figure 2 for A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements
Figure 3 for A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements
Figure 4 for A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements
* 23 pages, 7 figures, 38 references 
  Access Paper or Ask Questions

One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation


Nov 24, 2021
Zhichao Wang, Qicong Xie, Tao Li, Hongqiang Du, Lei Xie, Pengcheng Zhu, Mengxiao Bi

* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology


Nov 23, 2021
Tian Cai, Li Xie, Muge Chen, Yang Liu, Di He, Shuo Zhang, Cameron Mura, Philip E. Bourne, Lei Xie

Figure 1 for Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology
Figure 2 for Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology
Figure 3 for Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology
Figure 4 for Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology
* 18 pages, 6 figures 
  Access Paper or Ask Questions

S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement


Nov 16, 2021
Shubo Lv, Yihui Fu, Mengtao Xing, Jiayao Sun, Lei Xie, Jun Huang, Yannan Wang, Tao Yu

Figure 1 for S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement
Figure 2 for S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement
Figure 3 for S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement
Figure 4 for S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation


Nov 11, 2021
Yihui Fu, Yun Liu, Jingdong Li, Dawei Luo, Shubo Lv, Yukai Jv, Lei Xie

Figure 1 for Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
Figure 2 for Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
Figure 3 for Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition


Oct 18, 2021
Binbin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di Wu, Zhendong Peng

Figure 1 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 2 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 3 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 4 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

  Access Paper or Ask Questions

VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis


Oct 17, 2021
Yongmao Zhang, Jian Cong, Heyang Xue, Lei Xie, Pengcheng Zhu, Mengxiao Bi

Figure 1 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 2 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 3 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 4 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
* 5 pages, submitted to ICASSP 2022 
  Access Paper or Ask Questions

Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning


Oct 15, 2021
Li Zhang, Qing Wang, Lei Xie

Figure 1 for Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning
Figure 2 for Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning
Figure 3 for Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning
Figure 4 for Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning

  Access Paper or Ask Questions

M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge


Oct 14, 2021
Fan Yu, Shiliang Zhang, Yihui Fu, Lei Xie, Siqi Zheng, Zhihao Du, Weilong Huang, Pengcheng Guo, Zhijie Yan, Bin Ma, Xin Xu, Hui Bu

Figure 1 for M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
Figure 2 for M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
Figure 3 for M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
Figure 4 for M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
* 5 pages 
  Access Paper or Ask Questions

Controllable cross-speaker emotion transfer for end-to-end speech synthesis


Sep 14, 2021
Tao Li, Xinsheng Wang, Qicong Xie, Zhichao Wang, Lei Xie

Figure 1 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 2 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 3 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 4 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis

  Access Paper or Ask Questions

Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021


Sep 08, 2021
Li Zhang, Huan Zhao, Qinling Meng, Yanli Chen, Min Liu, Lei Xie

Figure 1 for Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021

  Access Paper or Ask Questions

AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person


Aug 11, 2021
Xinsheng Wang, Qicong Xie, Jihua Zhu, Lei Xie, Scharenborg

Figure 1 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 2 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 3 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 4 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person

  Access Paper or Ask Questions

Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion


Jun 26, 2021
Zhichao Wang, Xinyong Zhou, Fengyu Yang, Tao Li, Hongqiang Du, Lei Xie, Wendong Gan, Haitao Chen, Hai Li

Figure 1 for Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
Figure 2 for Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
Figure 3 for Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
Figure 4 for Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions

Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis


Jun 22, 2021
Jian Cong, Shan Yang, Lei Xie, Dan Su

Figure 1 for Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
Figure 2 for Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
Figure 3 for Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
Figure 4 for Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
* Accepted to INTERSPEECH 2021 
  Access Paper or Ask Questions

Controllable Context-aware Conversational Speech Synthesis


Jun 21, 2021
Jian Cong, Shan Yang, Na Hu, Guangzhi Li, Lei Xie, Dan Su

Figure 1 for Controllable Context-aware Conversational Speech Synthesis
Figure 2 for Controllable Context-aware Conversational Speech Synthesis
Figure 3 for Controllable Context-aware Conversational Speech Synthesis
Figure 4 for Controllable Context-aware Conversational Speech Synthesis
* Accepted to INTERSPEECH 2021 
  Access Paper or Ask Questions

Improving robustness of one-shot voice conversion with deep discriminative speaker encoder


Jun 19, 2021
Hongqiang Du, Lei Xie

Figure 1 for Improving robustness of one-shot voice conversion with deep discriminative speaker encoder
Figure 2 for Improving robustness of one-shot voice conversion with deep discriminative speaker encoder
Figure 3 for Improving robustness of one-shot voice conversion with deep discriminative speaker encoder
Figure 4 for Improving robustness of one-shot voice conversion with deep discriminative speaker encoder

  Access Paper or Ask Questions

Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS


Jun 18, 2021
Xiaochun An, Frank K. Soong, Lei Xie

Figure 1 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 2 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 3 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 4 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS

  Access Paper or Ask Questions

Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification


Jun 17, 2021
Li Zhang, Qing Wang, Kong Aik Lee, Lei Xie, Haizhou Li

Figure 1 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 2 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 3 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 4 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification

  Access Paper or Ask Questions

Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition


Jun 17, 2021
Xiong Wang, Sining Sun, Lei Xie, Long Ma

Figure 1 for Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition
Figure 2 for Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition
Figure 3 for Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition
Figure 4 for Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition

  Access Paper or Ask Questions

DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement


Jun 16, 2021
Shubo Lv, Yanxin Hu, Shimin Zhang, Lei Xie

Figure 1 for DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement
Figure 2 for DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement
Figure 3 for DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement
Figure 4 for DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement

  Access Paper or Ask Questions

F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement


Jun 16, 2021
Shimin Zhang, Yuxiang Kong, Shubo Lv, Yanxin Hu, Lei Xie

Figure 1 for F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement
Figure 2 for F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement
Figure 3 for F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement
Figure 4 for F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions

Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain


Jun 16, 2021
Pengcheng Guo, Xuankai Chang, Shinji Watanabe, Lei Xie

Figure 1 for Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
Figure 2 for Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
Figure 3 for Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
Figure 4 for Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions