Simultaneous Translation for Unsegmented Input: A Sliding Window Approach
This addresses a specific bottleneck in simultaneous spoken language translation systems, offering an incremental improvement for real-time applications.
The paper tackles the problem of translation quality degradation in spoken language translation due to erroneous segmentation of ASR outputs, especially in simultaneous settings, by proposing a sliding window approach that translates raw ASR outputs without relying on automatic segmenters, resulting in improvements of 1.3-2.0 BLEU points over the pipeline method and reduced flicker.
In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous segmentation, due to poor sentence-final punctuation by the ASR system, leads to degradation in translation quality, especially in the simultaneous (online) setting where the input is continuously updated. To reduce the influence of automatic segmentation, we present a sliding window approach to translate raw ASR outputs (online or offline) without needing to rely on an automatic segmenter. We train translation models using parallel windows (instead of parallel sentences) extracted from the original training data. At test time, we translate at the window level and join the translated windows using a simple approach to generate the final translation. Experiments on English-to-German and English-to-Czech show that our approach improves 1.3--2.0 BLEU points over the usual ASR-segmenter pipeline, and the fixed-length window considerably reduces flicker compared to a baseline retranslation-based online SLT system.