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

Add to Chrome

Add to Firefox

Picture for Shinji Watanabe

Shinji Watanabe

ESPnet-ONNX: Bridging a Gap Between Research and Production

Sep 20, 2022
Masao Someki, Yosuke Higuchi, Tomoki Hayashi, Shinji Watanabe

Figure 1 for ESPnet-ONNX: Bridging a Gap Between Research and Production

Figure 2 for ESPnet-ONNX: Bridging a Gap Between Research and Production

Figure 3 for ESPnet-ONNX: Bridging a Gap Between Research and Production

Figure 4 for ESPnet-ONNX: Bridging a Gap Between Research and Production

* Accepted to APSIPA ASC 2022

Access Paper or Ask Questions

ASR2K: Speech Recognition for Around 2000 Languages without Audio

Sep 06, 2022
Xinjian Li, Florian Metze, David R Mortensen, Alan W Black, Shinji Watanabe

Figure 1 for ASR2K: Speech Recognition for Around 2000 Languages without Audio

Figure 2 for ASR2K: Speech Recognition for Around 2000 Languages without Audio

Figure 3 for ASR2K: Speech Recognition for Around 2000 Languages without Audio

Figure 4 for ASR2K: Speech Recognition for Around 2000 Languages without Audio

* INTERSPEECH 2022

Access Paper or Ask Questions

VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Aug 03, 2022
Jiatong Shi, George Saon, David Haws, Shinji Watanabe, Brian Kingsbury

Figure 1 for VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Figure 2 for VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Figure 3 for VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Figure 4 for VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

* Interspeech 2022 accepted paper

Access Paper or Ask Questions

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Jul 19, 2022
Yen-Ju Lu, Xuankai Chang, Chenda Li, Wangyou Zhang, Samuele Cornell, Zhaoheng Ni, Yoshiki Masuyama, Brian Yan, Robin Scheibler, Zhong-Qiu Wang, Yu Tsao, Yanmin Qian, Shinji Watanabe

Figure 1 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Figure 2 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Figure 3 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Figure 4 for ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

* To appear in Interspeech 2022

Access Paper or Ask Questions

Two-Pass Low Latency End-to-End Spoken Language Understanding

Jul 14, 2022
Siddhant Arora, Siddharth Dalmia, Xuankai Chang, Brian Yan, Alan Black, Shinji Watanabe

Figure 1 for Two-Pass Low Latency End-to-End Spoken Language Understanding

Figure 2 for Two-Pass Low Latency End-to-End Spoken Language Understanding

Figure 3 for Two-Pass Low Latency End-to-End Spoken Language Understanding

Figure 4 for Two-Pass Low Latency End-to-End Spoken Language Understanding

* INTERSPEECH 2022

Access Paper or Ask Questions

Improving Speech Enhancement through Fine-Grained Speech Characteristics

Jul 11, 2022
Muqiao Yang, Joseph Konan, David Bick, Anurag Kumar, Shinji Watanabe, Bhiksha Raj

Figure 1 for Improving Speech Enhancement through Fine-Grained Speech Characteristics

Figure 2 for Improving Speech Enhancement through Fine-Grained Speech Characteristics

Figure 3 for Improving Speech Enhancement through Fine-Grained Speech Characteristics

Figure 4 for Improving Speech Enhancement through Fine-Grained Speech Characteristics

* Accepted at InterSpeech 2022

Access Paper or Ask Questions

Online Continual Learning of End-to-End Speech Recognition Models

Jul 11, 2022
Muqiao Yang, Ian Lane, Shinji Watanabe

Figure 1 for Online Continual Learning of End-to-End Speech Recognition Models

Figure 2 for Online Continual Learning of End-to-End Speech Recognition Models

Figure 3 for Online Continual Learning of End-to-End Speech Recognition Models

Figure 4 for Online Continual Learning of End-to-End Speech Recognition Models

* Accepted at InterSpeech 2022

Access Paper or Ask Questions