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 Leyuan Qu

Leyuan Qu
Alert button

Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition


Feb 21, 2023
Leyuan Qu, Cornelius Weber, Stefan Wermter

Add code
Alert button

Figure 1 for Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
Figure 2 for Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
Figure 3 for Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
Figure 4 for Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
* Neural Networks, Volume 161, April 2023, Pages 494-504 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Disentangling Prosody Representations with Unsupervised Speech Reconstruction


Dec 14, 2022
Leyuan Qu, Taihao Li, Cornelius Weber, Theresa Pekarek-Rosin, Fuji Ren, Stefan Wermter

Add code
Alert button

Figure 1 for Disentangling Prosody Representations with Unsupervised Speech Reconstruction
Figure 2 for Disentangling Prosody Representations with Unsupervised Speech Reconstruction
Figure 3 for Disentangling Prosody Representations with Unsupervised Speech Reconstruction
Figure 4 for Disentangling Prosody Representations with Unsupervised Speech Reconstruction

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition


Nov 16, 2022
Leyuan Qu, Wei Wang, Taihao Li, Cornelius Weber, Stefan Wermter, Fuji Ren

Add code
Alert button

Figure 1 for Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition
Figure 2 for Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition
Figure 3 for Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition
Figure 4 for Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning


Feb 27, 2022
Gerald Schwiebert, Cornelius Weber, Leyuan Qu, Henrique Siqueira, Stefan Wermter

Add code
Alert button

Figure 1 for A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning
Figure 2 for A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning
Figure 3 for A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning
Figure 4 for A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning
* Submitted to LREC 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading


Dec 09, 2021
Leyuan Qu, Cornelius Weber, Stefan Wermter

Add code
Alert button

Figure 1 for LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading
Figure 2 for LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading
Figure 3 for LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading
Figure 4 for LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading
* SUBMITTED TO IEEE Transaction on Neural Networks and Learning Systems 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email