Picture for Jumon Nozaki

Jumon Nozaki

Addressing Segmentation Ambiguity in Neural Linguistic Steganography

Add code
Nov 12, 2022
Viaarxiv icon

End-to-end Speech-to-Punctuated-Text Recognition

Add code
Jul 07, 2022
Figure 1 for End-to-end Speech-to-Punctuated-Text Recognition
Figure 2 for End-to-end Speech-to-Punctuated-Text Recognition
Figure 3 for End-to-end Speech-to-Punctuated-Text Recognition
Figure 4 for End-to-end Speech-to-Punctuated-Text Recognition
Viaarxiv icon

A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation

Add code
Oct 11, 2021
Figure 1 for A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Figure 2 for A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Figure 3 for A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Figure 4 for A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Viaarxiv icon

Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions

Add code
Apr 06, 2021
Figure 1 for Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
Figure 2 for Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
Figure 3 for Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
Figure 4 for Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
Viaarxiv icon