Spoken Language Understanding (SLU) is a critical component of voice
assistants; it consists of converting speech to semantic parses for task
execution. Previous works have explored end-to-end models to improve the
quality and robustness of SLU models with Deliberation, however these models
have remained autoregressive, resulting in higher latencies. In this work we
introduce PRoDeliberation, a novel method leveraging a Connectionist Temporal
Classification-based decoding strategy as well as a denoising objective to
train robust non-autoregressive deliberation models. We show that
PRoDeliberation achieves the latency reduction of parallel decoding (2-10x
improvement over autoregressive models) while retaining the ability to correct
Automatic Speech Recognition (ASR) mistranscriptions of autoregressive
deliberation systems. We further show that the design of the denoising training
allows PRoDeliberation to overcome the limitations of small ASR devices, and we
provide analysis on the necessity of each component of the system.

Spoken Language Understanding (SLU) 的关键组成部分是将语音转化为语义分析，以便进行任务执行。本研究介绍了 PRoDeliberation，一种利用基于连接主义时间分类的解码策略和降噪目标来训练稳健的非自回归思考模型的新方法。我们展示了 PRoDeliberation 实现了并行解码的延迟降低（比自回归模型提高 2-10 倍），同时保持了修正自回归思考系统的自动语音识别（ASR）误识别的能力。此外，我们进一步展示了降噪训练的设计使得 PRoDeliberation 能够克服小型 ASR 设备的限制，并对系统的每个组件的必要性进行了分析。