RNN transducer models for spoken language understandingSamuel ThomasHong-Kwang J. Kuoet al.2021ICASSP 2021
Robustness and Diversity Seeking Data-Free Knowledge DistillationPengchao HanJihong Parket al.2021ICASSP 2021
EAT: Enhanced ASR-TTS for self-supervised speech recognitionMurali Karthick BaskarLukáš Burgetet al.2021ICASSP 2021
Advancing RNN transducer technology for speech recognitionGeorge SaonZoltan Tuskeet al.2021ICASSP 2021