A context-aware knowledge transferring strategy for CTC-based ASR
This work addresses a specific limitation in non-autoregressive ASR for speech recognition, representing an incremental improvement.
The paper tackles the performance barrier in CTC-based ASR due to the independence assumption between tokens by proposing a context-aware knowledge transferring strategy, resulting in improved performance on AISHELL-1 and AISHELL-2 datasets.
Non-autoregressive automatic speech recognition (ASR) modeling has received increasing attention recently because of its fast decoding speed and superior performance. Among representatives, methods based on the connectionist temporal classification (CTC) are still a dominating stream. However, the theoretically inherent flaw, the assumption of independence between tokens, creates a performance barrier for the school of works. To mitigate the challenge, we propose a context-aware knowledge transferring strategy, consisting of a knowledge transferring module and a context-aware training strategy, for CTC-based ASR. The former is designed to distill linguistic information from a pre-trained language model, and the latter is framed to modulate the limitations caused by the conditional independence assumption. As a result, a knowledge-injected context-aware CTC-based ASR built upon the wav2vec2.0 is presented in this paper. A series of experiments on the AISHELL-1 and AISHELL-2 datasets demonstrate the effectiveness of the proposed method.