Non-autoregressive Transformer ASR With Ctc-enhanced Decoder Input

Abstract

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a fixed-length sequence filled with MASK tokens or a redundant sequence copied from encoder states as decoder input, they cannot provide efficient target-side information thus leading to accuracy degradation. To address this problem, we propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimental results show that our method outperforms all previous NAR counterparts and achieves 50x faster decoding speed than a strong AR baseline with only 0.0 ~ 0.3 absolute CER degradation on Aishell-1 and Aishell-2 datasets.

Stats

• citations28
• S2 citations—
• github stars0
• HF likes0
• heat score10.97
• arxiv keysong2020non

Related papers

• Linguistic-enhanced Transformer With CTC Embedding For Speech Recognition (2022)2.26
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Non-autoregressive Transformer With Unified Bidirectional Decoder For Automatic Speech Recognition (2021)7.81
• TSNAT: Two-step Non-autoregressvie Transformer Models For Speech Recognition (2021)10.61
• Improving Non-autoregressive End-to-end Speech Recognition With Pre-trained Acoustic And Language Models (2022)10.07
• A CTC Alignment-based Non-autoregressive Transformer For End-to-end Automatic Speech Recognition (2023)10.97
• An Improved Single Step Non-autoregressive Transformer For Automatic Speech Recognition (2021)0.00
• Non-autoregressive End-to-end Approaches For Joint Automatic Speech Recognition And Spoken Language Understanding (2023)5.84