16 citations · 44 across the 18 of their papers we have counts for
3 papers · 2 filters
Federated Learning in ASR: Not as Easy as You Think
Wentao Yu, Jan Freiwald, Sören Tewes +2
With the growing availability of smart devices and cloud services, personal speech assistance systems are increasingly used on a daily basis. Most devices redirect the voice record…
Large-vocabulary Audio-visual Speech Recognition in Noisy Environments
Wentao Yu, Steffen Zeiler, Dorothea Kolossa
Audio-visual speech recognition (AVSR) can effectively and significantly improve the recognition rates of small-vocabulary systems, compared to their audio-only counterparts. For l…
Fusing information streams in end-to-end audio-visual speech recognition
Wentao Yu, Steffen Zeiler, Dorothea Kolossa
End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides v…