With the increased applications of automatic speech recognition (ASR) in
recent years, it is essential to automatically insert punctuation marks and
remove disfluencies in transcripts, to improve the readability of the
transcripts as well as the performance of subsequent applications, such as
machine translation, dialogue systems, and so forth. In this paper, we propose
a Controllable Time-delay Transformer (CT-Transformer) model that jointly
completes the punctuation prediction and disfluency detection tasks in real
time. The CT-Transformer model facilitates freezing partial outputs with
controllable time delay to fulfill the real-time constraints in partial
decoding required by subsequent applications. We further propose a fast
decoding strategy to minimize latency while maintaining competitive
performance. Experimental results on the IWSLT2011 benchmark dataset and an
in-house Chinese annotated dataset demonstrate that the proposed approach
outperforms the previous state-of-the-art models on F-scores and achieves a
competitive inference speed.

本文提出了一种能够实时完成插入标点符号和去除语言障碍的强调时间延迟变压器模型，为后续的机器翻译、对话系统等应用提高了可读性和性能。在 IWSLT2011 基准数据集和中文注释数据集上的实验证实，该方法在 F-score 上的表现优于之前的最佳模型，并达到了竞争性的推理速度。