Saved in:
Bibliographic Details
Main Authors: Xu, Xi, Xu, Wenda, Ouyang, Siqi, Li, Lei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.16011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913557694644224
author Xu, Xi
Xu, Wenda
Ouyang, Siqi
Li, Lei
author_facet Xu, Xi
Xu, Wenda
Ouyang, Siqi
Li, Lei
contents Simultaneous speech translation (SimulST) systems must balance translation quality with response time, making latency measurement crucial for evaluating their real-world performance. However, there has been a longstanding belief that current metrics yield unrealistically high latency measurements in unsegmented streaming settings. In this paper, we investigate this phenomenon, revealing its root cause in a fundamental misconception underlying existing latency evaluation approaches. We demonstrate that this issue affects not only streaming but also segment-level latency evaluation across different metrics. Furthermore, we propose a modification to correctly measure computation-aware latency for SimulST systems, addressing the limitations present in existing metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16011
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
Xu, Xi
Xu, Wenda
Ouyang, Siqi
Li, Lei
Computation and Language
Artificial Intelligence
Simultaneous speech translation (SimulST) systems must balance translation quality with response time, making latency measurement crucial for evaluating their real-world performance. However, there has been a longstanding belief that current metrics yield unrealistically high latency measurements in unsegmented streaming settings. In this paper, we investigate this phenomenon, revealing its root cause in a fundamental misconception underlying existing latency evaluation approaches. We demonstrate that this issue affects not only streaming but also segment-level latency evaluation across different metrics. Furthermore, we propose a modification to correctly measure computation-aware latency for SimulST systems, addressing the limitations present in existing metrics.
title CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.16011