Recent Developments on Espnet Toolkit Boosted By Conformer
| Autor: | Tomoki Hayashi, Wangyou Zhang, Jing Shi, Hirofumi Inaguma, Daniel Garcia-Romero, Chenda Li, Xuankai Chang, Shinji Watanabe, Jiatong Shi, Kun Wei, Yuekai Zhang, Pengcheng Guo, Yosuke Higuchi, Naoyuki Kamo, Florian Boyer |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Signal processing Open source Audio and Speech Processing (eess.AS) Computer science Speech recognition Research community FOS: Electrical engineering electronic engineering information engineering Speech processing Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing Transformer (machine learning model) |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp39728.2021.9414858 |
| Popis: | 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 as automatic speech recognition (ASR), speech translations (ST), speech separation (SS) and text-to-speech (TTS). Our experiments reveal various training tips and significant performance benefits obtained with the Conformer on different tasks. These results are competitive or even outperform the current state-of-art Transformer models. We are preparing to release all-in-one recipes using open source and publicly available corpora for all the above tasks with pre-trained models. Our aim for this work is to contribute to our research community by reducing the burden of preparing state-of-the-art research environments usually requiring high resources. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|