EURO: Espnet Unsupervised ASR Open-source Toolkit

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 data

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keygao2022euro

Related papers

• Espnet-tts: Unified, Reproducible, And Integratable Open Source End-to-end Text-to-speech Toolkit (2019)23.32
• Espnet: End-to-end Speech Processing Toolkit (2018)22.17
• Espnet-se: End-to-end Speech Enhancement And Separation Toolkit Designed For Asr Integration (2020)13.55
• Espnet-spk: Full Pipeline Speaker Embedding Toolkit With Reproducible Recipes, Self-supervised Front-ends, And Off-the-shelf Models (2024)0.00
• Espresso: A Fast End-to-end Neural Speech Recognition Toolkit (2019)0.00
• The 2020 Espnet Update: New Features, Broadened Applications, Performance Improvements, And Future Plans (2020)18.20
• User-friendly Automatic Transcription Of Low-resource Languages: Plugging Espnet Into Elpis (2020)2.26
• Espnet-se++: Speech Enhancement For Robust Speech Recognition, Translation, And Understanding (2022)18.72