
Qiushi Zhu
audio-visual speech recognition
representation learning
noise-robustness
viseme-phoneme mapping
modality transfer
multichannel multi-modal speech
2
presentations
13
number of views
SHORT BIO
I am a dedicated Ph.D. candidate at the University of Science and Technology of China (USTC), actively engaged in the field of Speech Recognition. My primary research focuses on robust speech recognition and multimodal speech recognition.
Presentations

Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation | VIDEO
Qiushi Zhu and 4 other authors

Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition
Yuchen Hu and 5 other authors