.png){kind=icon}
返回
Sequence-to-Sequence Models for Emphasis Speech Translation
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2018.2846402.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Speech-to-speech translation (S2ST) systems are capable of breaking language barriers in cross-lingual communication by translating speech across languages. Recent studies have introduced many improvements that allow existing S2ST systems to handle not only linguistic meaning hut also paralinguistic information such as emphasis by proposing additional emphasis estimation and translation components. However, the approach used for emphasis translation is not optimal for sequence translation tasks and fails to easily handle the long-term dependencies of words and emphasis levels. It also requires the quantization of emphasis levels and treats them asdiscrete labels instead of continuous values. Moreover, the whole translation pipeline is fairly complexand slow because all components are trained separately without joint optimization. In this paper, we make two contributions: 1) we propose an approach that can handle continuous emphasis levels based on sequence-to-sequence models, and 2) we combine machine and emphasis translation into a single model, which greatly simplifies the translation pipeline and make it easier to perform joint optimization. Our results on an emphasis translation task indicate that our translation models outperform previous models by a large margin in both objective and subjective tests. Experiments on a joint translation model also show that our models can perform joint translation of words and emphasis with one-word delays instead of full-sentence delays while preserving the translation performance of both tasks.
Keyword:
Emphasis estimation
emphasis translation
speech-to-speech translation (S2ST)
joint optimization of words and emphasis
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Tracking Late Cretaceous environmental change: Geochemical environment of the upper Campanian to lower Maastrichtian chalks at Kronsmoor, northern Germany追踪晚白垩世环境变化：德国北部克罗恩斯穆尔地区上坎帕阶至下马斯特里赫阶白垩岩的地球化学环境
PREAI
分享收藏The dodeca-coordinated La©B8C4+/0/− molecular wheels: conflicting aromaticity versus double aromaticity.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAI分享收藏Early Aptian paleoenvironmental evolution of the Bab Basin at the southern Neo‐Tethys margin: Response to global carbon‐cycle perturbations across Ocean Anoxic Event 1a巴盆地在 Neo-Tethys 南缘的早阿普第期古环境演化：对大洋缺氧事件1a期间全球碳循环扰动的响应
OAAI
OAAI分享收藏Magmatic evolution of the Early Pliocene Etrüsk stratovolcano, Eastern Anatolian Collision Zone, Turkey土耳其东部安纳托利亚碰撞带早皮亚琴察时代Etrüsk层状火山岩浆演化Lithos
LithosIF0
PREAI
分享收藏First-Principle Protocol for Calculating Ionization Energies and Redox Potentials of Solvated Molecules and Ions: Theory and Application to Aqueous Phenol and Phenolate计算溶剂化分子和离子的电离能和氧化还原电位的第一原理协议: 理论和对苯酚和酚盐水溶液的应用OAAI
OAAI分享收藏
查看更多内容