Recent Developments on ESPnet Toolkit Boosted by Conformer

• Published in: arXiv.org
• Main Authors: Guo, Pengcheng, Boyer, Florian, Chang, Xuankai, Hayashi, Tomoki, Higuchi, Yosuke, Inaguma, Hirofumi, Kamo, Naoyuki, Li, Chenda, Garcia-Romero, Daniel, Shi, Jiatong, Shi, Jing, Watanabe, Shinji, Wei, Kun, Zhang, Wangyou, Zhang, Yuekai
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.10.2020
• Subjects: Automatic speech recognition; Convolution; Speech; Speech processing; Toolkits; Transformers; Translations

In this study, we present recent developments on ESPnet: End-to-End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-augmented Transformer. This paper shows the results for a wide range of end-to-end speech processing applications, such...