Alert button
Picture for Tetsuji Ogawa

Tetsuji Ogawa

Alert button

BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model

Oct 29, 2022
Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe

Figure 1 for BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Figure 2 for BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Figure 3 for BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Figure 4 for BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Viaarxiv icon

Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation

Mar 26, 2022
Kohei Saijo, Tetsuji Ogawa

Figure 1 for Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Figure 2 for Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Figure 3 for Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Viaarxiv icon

An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR

Oct 20, 2021
Huaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi

Figure 1 for An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
Figure 2 for An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
Figure 3 for An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
Viaarxiv icon

Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units

Oct 08, 2021
Yosuke Higuchi, Keita Karube, Tetsuji Ogawa, Tetsunori Kobayashi

Figure 1 for Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Figure 2 for Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Figure 3 for Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Figure 4 for Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Viaarxiv icon

Improved Mask-CTC for Non-Autoregressive End-to-End ASR

Oct 26, 2020
Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi

Figure 1 for Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Figure 2 for Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Figure 3 for Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Viaarxiv icon

Block-wise Scrambled Image Recognition Using Adaptation Network

Jan 21, 2020
Koki Madono, Masayuki Tanaka, Masaki Onishi, Tetsuji Ogawa

Figure 1 for Block-wise Scrambled Image Recognition Using Adaptation Network
Figure 2 for Block-wise Scrambled Image Recognition Using Adaptation Network
Figure 3 for Block-wise Scrambled Image Recognition Using Adaptation Network
Figure 4 for Block-wise Scrambled Image Recognition Using Adaptation Network
Viaarxiv icon