Advancing CTC-CRF Based End-to-end Speech Recognition With Wordpieces And Conformers

Abstract

Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid approach and the simplicity of the end-to-end approach. In this paper, we further advance CTC-CRF based ASR technique with explorations on modeling units and neural architectures. Specifically, we investigate techniques to enable the recently developed wordpiece modeling units and Conformer neural networks to be succesfully applied in CTC-CRFs. Experiments are conducted on two English datasets (Switchboard, Librispeech) and a German dataset from CommonVoice. Experimental results suggest that (i) Conformer can improve the recognition performance significantly; (ii) Wordpiece-based systems perform slightly worse compared with phone-based systems for the target language with a low degree of grapheme-phoneme correspondence (e.g. English), while the two syst

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzheng2021advancing

Related papers

• Faster, Simpler And More Accurate Hybrid ASR Systems Using Wordpieces (2020)9.41
• Advances In All-neural Speech Recognition (2016)11.29
• CAT: Crf-based ASR Toolkit (2019)0.00
• CAT: A CTC-CRF Based ASR Toolkit Bridging The Hybrid And The End-to-end Approaches Towards Data Efficiency And Low Latency (2020)9.03
• An Improved Hybrid Ctc-attention Model For Speech Recognition (2018)0.00
• Multitask Learning With CTC And Segmental CRF For Speech Recognition (2017)0.00
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76