Jaesong Lee, Soyoon Kim, Hanbyul Kim, Joon Son Chung
TL;DR提出了一种小型模型的分段模型,使用 ASR 语音识别与标点任务作为前训练策略并将其整合到 ST 系统中,以提高语音翻译质量。
Abstract
speech segmentation is an essential part of speech translation (ST) systems
in real-world scenarios. Since most ST models are designed to process speech
segments, long-form audio must be partitioned into shorter