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

Add to Chrome

Add to Firefox

Picture for Zexin Cai

Zexin Cai

Invertible Voice Conversion

Jan 26, 2022
Zexin Cai, Ming Li

Figure 1 for Invertible Voice Conversion

Figure 2 for Invertible Voice Conversion

Figure 3 for Invertible Voice Conversion

Figure 4 for Invertible Voice Conversion

* 5-page conference paper

Access Paper or Ask Questions

The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

Apr 11, 2021
Yechen Wang, Yan Jia, Murong Ma, Zexin Cai, Ming Li

Figure 1 for The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

Figure 2 for The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

Figure 3 for The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

Figure 4 for The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

* 5 pages, 1 figures, submitted to INTERSPEECH

Access Paper or Ask Questions

Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Nov 03, 2020
Yan Jia, Zexin Cai, Murong Ma, Zeqing Zhao, Xuyang Wang, Junjie Wang, Ming Li

Figure 1 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 2 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 3 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 4 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

* Submitted to ICASSP 2021

Access Paper or Ask Questions

Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

May 21, 2020
Zexin Cai, Yaogen Yang, Ming Li

Figure 1 for Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

Figure 2 for Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

Figure 3 for Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

Figure 4 for Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

* in preparation for Neural Networks journal Special issue on Advances in Deep Learning Based Speech Processing

Access Paper or Ask Questions

From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

May 15, 2020
Zexin Cai, Chuxiong Zhang, Ming Li

Figure 1 for From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

Figure 2 for From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

Figure 3 for From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

Figure 4 for From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

* Submitted to INTERSPEECH 2020

Access Paper or Ask Questions

Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features

Jul 03, 2019
Zexin Cai, Yaogen Yang, Chuxiong Zhang, Xiaoyi Qin, Ming Li

Figure 1 for Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features

Figure 2 for Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features

Figure 3 for Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features

* 5 pages, 1 figure, 2 tables, submit to INTERSPEECH 2019

Access Paper or Ask Questions

End-to-end Language Identification using NetFV and NetVLAD

Sep 09, 2018
Jinkun Chen, Weicheng Cai, Danwei Cai, Zexin Cai, Haibin Zhong, Ming Li

Figure 1 for End-to-end Language Identification using NetFV and NetVLAD

Figure 2 for End-to-end Language Identification using NetFV and NetVLAD

Figure 3 for End-to-end Language Identification using NetFV and NetVLAD

* Accepted for ISCSLP 2018

Access Paper or Ask Questions