EURO: ESPnet Unsupervised ASR Open-source Toolkit

TL;DR

EURO is an open-source toolkit for unsupervised speech recognition that integrates multiple self-supervised models and decoding strategies, achieving state-of-the-art results and promoting reproducibility in UASR research.

Contribution

It introduces EURO, a comprehensive, flexible, and efficient open-source toolkit for UASR based on ESPnet, extending functionality with multiple models and decoding methods.

Findings

Achieves state-of-the-art UASR performance on TIMIT and LibriSpeech.

Demonstrates effectiveness of integrating various self-supervised models.

Provides a unified pipeline for easier application and reproducibility.

Abstract

This paper describes the ESPnet Unsupervised ASR Open-source Toolkit (EURO), an end-to-end open-source toolkit for unsupervised automatic speech recognition (UASR). EURO adopts the state-of-the-art UASR learning method introduced by the Wav2vec-U, originally implemented at FAIRSEQ, which leverages self-supervised speech representations and adversarial training. In addition to wav2vec2, EURO extends the functionality and promotes reproducibility for UASR tasks by integrating S3PRL and k2, resulting in flexible frontends from 27 self-supervised models and various graph-based decoding strategies. EURO is implemented in ESPnet and follows its unified pipeline to provide UASR recipes with a complete setup. This improves the pipeline's efficiency and allows EURO to be easily applied to existing datasets in ESPnet. Extensive experiments on three mainstream self-supervised models demonstrate the toolkit's effectiveness and achieve state-of-the-art UASR performance on TIMIT and LibriSpeech datasets. EURO will be publicly available at https://github.com/espnet/espnet, aiming to promote this exciting and emerging research area based on UASR through open-source activity.