@inproceedings{tran-etal-2022-joint,
title = "Does Joint Training Really Help Cascaded Speech Translation?",
author = "Tran, Viet Anh Khoa and
Thulke, David and
Gao, Yingbo and
Herold, Christian and
Ney, Hermann",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.297",
doi = "10.18653/v1/2022.emnlp-main.297",
pages = "4480--4487",
abstract = "Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.However, fundamental challenges such as error propagation from the automatic speech recognition system still remain.To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods.In this work, we seek to answer the question of whether joint training really helps cascaded speech translation.We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities.Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training.We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2022-joint">
<titleInfo>
<title>Does Joint Training Really Help Cascaded Speech Translation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Anh</namePart>
<namePart type="given">Khoa</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Thulke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingbo</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Herold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.However, fundamental challenges such as error propagation from the automatic speech recognition system still remain.To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods.In this work, we seek to answer the question of whether joint training really helps cascaded speech translation.We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities.Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training.We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation.</abstract>
<identifier type="citekey">tran-etal-2022-joint</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.297</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.297</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4480</start>
<end>4487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Joint Training Really Help Cascaded Speech Translation?
%A Tran, Viet Anh Khoa
%A Thulke, David
%A Gao, Yingbo
%A Herold, Christian
%A Ney, Hermann
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F tran-etal-2022-joint
%X Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.However, fundamental challenges such as error propagation from the automatic speech recognition system still remain.To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods.In this work, we seek to answer the question of whether joint training really helps cascaded speech translation.We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities.Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training.We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation.
%R 10.18653/v1/2022.emnlp-main.297
%U https://aclanthology.org/2022.emnlp-main.297
%U https://doi.org/10.18653/v1/2022.emnlp-main.297
%P 4480-4487
Markdown (Informal)
[Does Joint Training Really Help Cascaded Speech Translation?](https://aclanthology.org/2022.emnlp-main.297) (Tran et al., EMNLP 2022)
ACL
- Viet Anh Khoa Tran, David Thulke, Yingbo Gao, Christian Herold, and Hermann Ney. 2022. Does Joint Training Really Help Cascaded Speech Translation?. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4480–4487, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.