Lune

ACL Findings2023

Towards Speech Dialogue Translation Mediating Speakers of Different Languages

Shuichiro Shimizu, Chenhui Chu, Sheng Li, Sadao Kurohashi

摘要

We present a new task, speech dialogue translation mediating speakers of different languages.We construct the SpeechBSD dataset for the task and conduct baseline experiments.Furthermore, we consider context to be an important aspect that needs to be addressed in this task and propose two ways of utilizing context, namely monolingual context and bilingual context.We conduct cascaded speech translation experiments using Whisper and mBART, and show that bilingual context performs better in our settings.彼は良い考えだと言ってました He said it's a good idea MT 少し甘いと思います I think it's a bit sweet MT What do you think about it?

问 Lune

尽管问,回答会引用原文。

Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

它引用的 Paper4

  1. Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman 等ICML 2023 · 6,966 次引用
  2. Towards Making the Most of Dialogue Characteristics for Neural Chat TranslationYunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu 等EMNLP 2021 · 12 次引用
  3. Beyond Sentence-Level End-to-End Speech Translation: Context HelpsBiao Zhang, Ivan Titov, Barry Haddow, Rico SennrichACL 2021
  4. Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta 等ACL 2021

相关 Paper

  1. ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue SummarizationJiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng 等EMNLP 2022 · 27 次引用
  2. Whisper-UT: A Unified Translation Framework for Speech and TextCihan Xiao, Matthew Wiesner, Debashish Chakraborty, Reno Kriz 等EMNLP 2025
  3. End-to-End Speech Translation for Code Switched SpeechOrion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan 等ACL Findings 2022 · 21 次引用
  4. MSCTD: A Multimodal Sentiment Chat Translation DatasetYunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen 等ACL 2022 · 27 次引用
  5. WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text AdaptabilityYongkang Yin, Yuexian ZouAAAI 2026
黄昏的海面,两侧是细线勾勒的悬崖