In this paper, we summarize the application of transformer and its streamable
variant, Emformer based acoustic model for large scale speech recognition
applications. We compare the transformer based acoustic models with their LSTM
counterparts on industrial scale tasks. Specifically, we compare Emformer with
latency-controlled BLSTM (LCBLSTM) on medium latency tasks and LSTM on low
latency tasks. On a low latency voice assistant task, Emformer gets 24% to 26%
relative word error rate reductions (WERRs). For medium latency scenarios,
comparing with LCBLSTM with similar model size and latency, Emformer gets
significant WERR across four languages in video captioning datasets with 2-3
times inference real-time factors reduction.

本文总结了 Transformer 和其可流式传输的变体 Emformer 在大规模语音识别应用中的应用。通过比较 Transformer 和 LSTM 模型在工业规模任务中的差异，介绍了 Emformer 在中等延迟任务和低延迟任务上与 LCBLSTM 和 LSTM 的性能比较。结果表明，Emformer 在低延迟语音助手任务中有 24％至 26％的相对单词错误率降低，并在视频字幕数据集中的四种语言中比 LCBLSTM 具有更优异的性能。