Picture for Manuel Giollo

Manuel Giollo

Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition

Add code
Dec 11, 2020
Figure 1 for Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition
Figure 2 for Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition
Figure 3 for Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition
Figure 4 for Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition
Viaarxiv icon

Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio

Add code
Nov 25, 2020
Figure 1 for Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio
Figure 2 for Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio
Figure 3 for Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio
Figure 4 for Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio
Viaarxiv icon