This paper analyzes the features of monotonic translations, which follow the
word order of the source language, in simultaneous interpreting (SI). The word
order differences are one of the biggest challenges in SI, especially for
language pairs with significant structural differences like English and
Japanese. We analyzed the characteristics of monotonic translations using the
NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset
and found some grammatical structures that make monotonic translation difficult
in English-Japanese SI. We further investigated the features of monotonic
translations through evaluating the output from the existing speech translation
(ST) and simultaneous speech translation (simulST) models on NAIST
English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset as well
as on existing test sets. The results suggest that the existing SI-based test
set underestimates the model performance. We also found that the
monotonic-translation-based dataset would better evaluate simulST models, while
using an offline-based test set for evaluating simulST models underestimates
the model performance.

分析同传中顺译特征，在英日语言对中特别是英语和日语这种具有显著结构差异的语言对中，词序差异是同传的最大挑战之一。通过使用 NAIST 的英日顺译数据集对顺译特征进行了分析，并发现了一些在英日同传中使顺译困难的语法结构。通过评估现有语音翻译和同传语音翻译模型在 NAIST 的英日顺译数据集和现有测试集上的输出，进一步研究了顺译特征。结果表明，现有的基于同传的测试集低估了模型的性能。同时，发现基于顺译的数据集可以更好地评估同传模型，而使用离线测试集评估同传模型会低估模型的性能。

英日同传中的词语顺序：基于分块单调翻译的分析与评估

Word Order in English-Japanese Simultaneous Interpretation: Analyses and  Evaluation using Chunk-wise Monotonic Translation

Speech-to-Speech and Speech-to-Text translation are currently dynamic areas
of research. To contribute to these fields, we present SpeechAlign, a framework
to evaluate the underexplored field of source-target alignment in speech
models. Our framework has two core components. First, to tackle the absence of
suitable evaluation datasets, we introduce the Speech Gold Alignment dataset,
built upon a English-German text translation gold alignment dataset. Secondly,
we introduce two novel metrics, Speech Alignment Error Rate (SAER) and
Time-weighted Speech Alignment Error Rate (TW-SAER), to evaluate alignment
quality in speech models. By publishing SpeechAlign we provide an accessible
evaluation framework for model assessment, and we employ it to benchmark
open-source Speech Translation models.

SpeechAlign 是一个框架，用于评估语音模型中源 - 目标对齐领域的尚未充分探索的领域，并提供了两个新的度量标准来评估语音模型的对齐质量，通过发布 SpeechAlign 来为模型评估提供一个可访问的评估框架，并用它来评估开源的语音翻译模型。