Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition
This work addresses the need for low-latency, high-accuracy speech recognition systems, particularly for real-time applications like voice assistants, and is incremental as it builds upon existing streaming attention-based methods.
The paper tackled the problem of streaming end-to-end speech recognition by proposing a novel online system using Streaming Chunk-Aware Multihead Attention and a latency control memory-equipped self-attention network, achieving a character error rate of 7.39% on the AISHELL-1 task, which is the best published performance for online ASR.
Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we propose a novel online E2E-ASR system by using Streaming Chunk-Aware Multihead Attention(SCAMA) and a latency control memory equipped self-attention network (LC-SAN-M). LC-SAN-M uses chunk-level input to control the latency of encoder. As to SCAMA, a jointly trained predictor is used to control the output of encoder when feeding to decoder, which enables decoder to generate output in streaming manner. Experimental results on the open 170-hour AISHELL-1 and an industrial-level 20000-hour Mandarin speech recognition tasks show that our approach can significantly outperform the MoChA-based baseline system under comparable setup. On the AISHELL-1 task, our proposed method achieves a character error rate (CER) of 7.39%, to the best of our knowledge, which is the best published performance for online ASR.