Picture for Toru Taniguchi

Toru Taniguchi

Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words

Add code
Aug 15, 2024
Viaarxiv icon

An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions

Add code
Apr 28, 2019
Figure 1 for An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
Figure 2 for An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
Figure 3 for An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
Viaarxiv icon

Speaker Selective Beamformer with Keyword Mask Estimation

Add code
Oct 25, 2018
Figure 1 for Speaker Selective Beamformer with Keyword Mask Estimation
Figure 2 for Speaker Selective Beamformer with Keyword Mask Estimation
Figure 3 for Speaker Selective Beamformer with Keyword Mask Estimation
Figure 4 for Speaker Selective Beamformer with Keyword Mask Estimation
Viaarxiv icon