Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Tatsuya Kawahara

Tatsuya Kawahara

Multi-Referenced Training for Dialogue Response Generation

Sep 15, 2020
Tianyu Zhao, Tatsuya Kawahara

Figure 1 for Multi-Referenced Training for Dialogue Response Generation

Figure 2 for Multi-Referenced Training for Dialogue Response Generation

Figure 3 for Multi-Referenced Training for Dialogue Response Generation

Figure 4 for Multi-Referenced Training for Dialogue Response Generation

Access Paper or Ask Questions

Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

Aug 09, 2020
Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Figure 1 for Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

Figure 2 for Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

Figure 3 for Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

Figure 4 for Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

* Accepted in INTERSPEECH2020

Access Paper or Ask Questions

Enhancing Monotonic Multihead Attention for Streaming ASR

May 23, 2020
Hirofumi Inaguma, Masato Mimura, Tatsuya Kawahara

Figure 1 for Enhancing Monotonic Multihead Attention for Streaming ASR

Figure 2 for Enhancing Monotonic Multihead Attention for Streaming ASR

Figure 3 for Enhancing Monotonic Multihead Attention for Streaming ASR

Figure 4 for Enhancing Monotonic Multihead Attention for Streaming ASR

* Corrected AISHELL-1 results

Access Paper or Ask Questions

Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

May 19, 2020
Kohei Matsuura, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Figure 1 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

Figure 2 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

Figure 3 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

Figure 4 for Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition

* Submitted to Interspeech 2020

Access Paper or Ask Questions

CTC-synchronous Training for Monotonic Attention Model

May 17, 2020
Hirofumi Inaguma, Masato Mimura, Tatsuya Kawahara

Figure 1 for CTC-synchronous Training for Monotonic Attention Model

Figure 2 for CTC-synchronous Training for Monotonic Attention Model

Figure 3 for CTC-synchronous Training for Monotonic Attention Model

Figure 4 for CTC-synchronous Training for Monotonic Attention Model

Access Paper or Ask Questions

Designing Precise and Robust Dialogue Response Evaluators

Apr 24, 2020
Tianyu Zhao, Divesh Lala, Tatsuya Kawahara

Figure 1 for Designing Precise and Robust Dialogue Response Evaluators

Figure 2 for Designing Precise and Robust Dialogue Response Evaluators

Figure 3 for Designing Precise and Robust Dialogue Response Evaluators

Figure 4 for Designing Precise and Robust Dialogue Response Evaluators

* Accepted at ACL 2020

Access Paper or Ask Questions