具有异步修正的动态延迟语音识别
Dynamic latency speech recognition with asynchronous revision
摘要：
在这项工作中，我们提出了一种推理技术，异步修订，统一流和非流语音识别模型。具体来说，我们实现动态延迟只有一个模型，通过使用任意的右上下文推理。该模型由用于音频编码的卷积层堆栈组成。在推理阶段，可以异步地修改编码器和解码器的历史状态，以在延迟和模型的准确性之间进行权衡。为了减轻训练和推理的不匹配，我们提出了一种训练技术，段裁剪，它随机地将输入的话语分成几个具有前向连接的段。这使我们能够获得动态延迟语音识别结果，并大大提高了准确性。实验结果表明，与流媒体模型相比，本文提出的基于异步修改的动态延迟模型相对性能提高了8%~ 14%.
英文摘要：
In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during inference. The model is composed of a stack of convolutional layers for audio encoding. In inference stage, the history states of encoder and decoder can be asynchronously revised to trade off between the latency and the accuracy of the model. To alleviate training and inference mismatch, we propose a training technique, segment cropping, which randomly splits input utterances into several segments with forward connections. This allows us to have dynamic latency speech recognition results with large improvements in accuracy. Experiments show that our dynamic latency model with asynchronous revision gives 8\%-14\% relative improvements over the streaming models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
