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

Add to Chrome

Add to Firefox

Picture for Cong Zhang

Cong Zhang

Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

Apr 14, 2022
Cong Zhang, Huinan Zeng, Huang Liu, Jiewen Zheng

Figure 1 for Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

Figure 2 for Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

Figure 3 for Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

Figure 4 for Applying Feature Underspecified Lexicon Phonological Features in Multilingual Text-to-Speech

* submitted to Interspeech 2022. arXiv admin note: substantial text overlap with arXiv:2110.03609

Access Paper or Ask Questions

ByT5 model for massively multilingual grapheme-to-phoneme conversion

Apr 06, 2022
Jian Zhu, Cong Zhang, David Jurgens

Figure 1 for ByT5 model for massively multilingual grapheme-to-phoneme conversion

Figure 2 for ByT5 model for massively multilingual grapheme-to-phoneme conversion

Figure 3 for ByT5 model for massively multilingual grapheme-to-phoneme conversion

Figure 4 for ByT5 model for massively multilingual grapheme-to-phoneme conversion

* Submitted to Interspeech 2022

Access Paper or Ask Questions

Applying Phonological Features in Multilingual Text-To-Speech

Oct 10, 2021
Cong Zhang, Huinan Zeng, Huang Liu, Jiewen Zheng

Figure 1 for Applying Phonological Features in Multilingual Text-To-Speech

Figure 2 for Applying Phonological Features in Multilingual Text-To-Speech

Figure 3 for Applying Phonological Features in Multilingual Text-To-Speech

* demo webpage: https://congzhang365.github.io/feature_tts/

Access Paper or Ask Questions

Phone-to-audio alignment without text: A Semi-supervised Approach

Oct 08, 2021
Jian Zhu, Cong Zhang, David Jurgens

Figure 1 for Phone-to-audio alignment without text: A Semi-supervised Approach

Figure 2 for Phone-to-audio alignment without text: A Semi-supervised Approach

Figure 3 for Phone-to-audio alignment without text: A Semi-supervised Approach

Figure 4 for Phone-to-audio alignment without text: A Semi-supervised Approach

* Submitted to ICASSP 2022

Access Paper or Ask Questions

Synchronising speech segments with musical beats in Mandarin and English singing

Jun 18, 2021
Cong Zhang, Jian Zhu

Figure 1 for Synchronising speech segments with musical beats in Mandarin and English singing

Figure 2 for Synchronising speech segments with musical beats in Mandarin and English singing

Figure 3 for Synchronising speech segments with musical beats in Mandarin and English singing

Figure 4 for Synchronising speech segments with musical beats in Mandarin and English singing

* To be published in the Proceeding of Interspeech 2021

Access Paper or Ask Questions

DeepFake-o-meter: An Open Platform for DeepFake Detection

Mar 02, 2021
Yuezun Li, Cong Zhang, Pu Sun, Honggang Qi, Siwei Lyu

Figure 1 for DeepFake-o-meter: An Open Platform for DeepFake Detection

Figure 2 for DeepFake-o-meter: An Open Platform for DeepFake Detection

Figure 3 for DeepFake-o-meter: An Open Platform for DeepFake Detection

* submitted to SAPDE 2021

Access Paper or Ask Questions