Streaming automatic speech recognition (ASR) aims to emit each hypothesized
word as quickly and accurately as possible, while full-context ASR waits for
the completion of a full speech utterance before emitting completed hypotheses.
In this work, we propose a unified framework, Dual-mode ASR, to train a single
end-to-end ASR model with shared weights for both streaming and full-context
speech recognition. We show that the latency and accuracy of streaming ASR
significantly benefit from weight sharing and joint training of full-context
ASR, especially with inplace knowledge distillation during the training. The
Dual-mode ASR framework can be applied to recent state-of-the-art
convolution-based and transformer-based ASR networks. We present extensive
experiments with two state-of-the-art ASR networks, ContextNet and Conformer,
on two datasets, a widely used public dataset LibriSpeech and a large-scale
dataset MultiDomain. Experiments and ablation studies demonstrate that
Dual-mode ASR not only simplifies the workflow of training and deploying
streaming and full-context ASR models, but also significantly improves both
emission latency and recognition accuracy of streaming ASR. With Dual-mode ASR,
we achieve new state-of-the-art streaming ASR results on both LibriSpeech and
MultiDomain in terms of accuracy and latency.

该研究提出了一种统一框架的双模 ASR（自动语音识别），通过权重共享和全场景 ASR 的联合训练，特别是在训练期间进行知识蒸馏，使流式 ASR 的延迟和准确性得到明显改善。该框架适用于最新的卷积和变压器 ASR 网络，并在 LibriSpeech 和 MultiDomain 数据集上进行了广泛实验和削减研究，取得了新的流式 ASR 结果。