Recent Developments on ESPnet Toolkit Boosted by Conformer

TL;DR

This paper discusses recent enhancements to the ESPnet toolkit, highlighting the integration of the Conformer architecture across various speech processing tasks, leading to improved performance and resource-efficient research.

Contribution

Introduces the integration of Conformer architecture into ESPnet, demonstrating its effectiveness across multiple speech tasks with open-source recipes and pre-trained models.

Findings

Conformer achieves competitive or superior results compared to state-of-the-art Transformers.

Training tips significantly improve Conformer performance.

Open-source recipes facilitate research and reduce resource barriers.

Abstract

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.