Alert button
Picture for Takaaki Hori

Takaaki Hori

Alert button

Back-Translation-Style Data Augmentation for End-to-End ASR

Jul 28, 2018
Tomoki Hayashi, Shinji Watanabe, Yu Zhang, Tomoki Toda, Takaaki Hori, Ramon Astudillo, Kazuya Takeda

Figure 1 for Back-Translation-Style Data Augmentation for End-to-End ASR
Figure 2 for Back-Translation-Style Data Augmentation for End-to-End ASR
Figure 3 for Back-Translation-Style Data Augmentation for End-to-End ASR
Figure 4 for Back-Translation-Style Data Augmentation for End-to-End ASR
Viaarxiv icon

End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features

Jun 30, 2018
Chiori Hori, Huda Alamri, Jue Wang, Gordon Wichern, Takaaki Hori, Anoop Cherian, Tim K. Marks, Vincent Cartillier, Raphael Gontijo Lopes, Abhishek Das, Irfan Essa, Dhruv Batra, Devi Parikh

Figure 1 for End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
Figure 2 for End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
Figure 3 for End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
Figure 4 for End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
Viaarxiv icon

A Purely End-to-end System for Multi-speaker Speech Recognition

May 15, 2018
Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

Figure 1 for A Purely End-to-end System for Multi-speaker Speech Recognition
Figure 2 for A Purely End-to-end System for Multi-speaker Speech Recognition
Figure 3 for A Purely End-to-end System for Multi-speaker Speech Recognition
Figure 4 for A Purely End-to-end System for Multi-speaker Speech Recognition
Viaarxiv icon

ESPnet: End-to-End Speech Processing Toolkit

Mar 30, 2018
Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai

Figure 1 for ESPnet: End-to-End Speech Processing Toolkit
Figure 2 for ESPnet: End-to-End Speech Processing Toolkit
Figure 3 for ESPnet: End-to-End Speech Processing Toolkit
Figure 4 for ESPnet: End-to-End Speech Processing Toolkit
Viaarxiv icon

End-to-end Conversation Modeling Track in DSTC6

Jan 30, 2018
Chiori Hori, Takaaki Hori

Figure 1 for End-to-end Conversation Modeling Track in DSTC6
Figure 2 for End-to-end Conversation Modeling Track in DSTC6
Figure 3 for End-to-end Conversation Modeling Track in DSTC6
Figure 4 for End-to-end Conversation Modeling Track in DSTC6
Viaarxiv icon

Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM

Jun 08, 2017
Takaaki Hori, Shinji Watanabe, Yu Zhang, William Chan

Figure 1 for Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
Figure 2 for Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
Figure 3 for Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
Viaarxiv icon

Multichannel End-to-end Speech Recognition

Mar 14, 2017
Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey

Figure 1 for Multichannel End-to-end Speech Recognition
Figure 2 for Multichannel End-to-end Speech Recognition
Figure 3 for Multichannel End-to-end Speech Recognition
Figure 4 for Multichannel End-to-end Speech Recognition
Viaarxiv icon

Attention-Based Multimodal Fusion for Video Description

Mar 09, 2017
Chiori Hori, Takaaki Hori, Teng-Yok Lee, Kazuhiro Sumi, John R. Hershey, Tim K. Marks

Figure 1 for Attention-Based Multimodal Fusion for Video Description
Figure 2 for Attention-Based Multimodal Fusion for Video Description
Figure 3 for Attention-Based Multimodal Fusion for Video Description
Figure 4 for Attention-Based Multimodal Fusion for Video Description
Viaarxiv icon

Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning

Jan 31, 2017
Suyoun Kim, Takaaki Hori, Shinji Watanabe

Figure 1 for Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
Figure 2 for Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
Figure 3 for Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
Figure 4 for Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
Viaarxiv icon