@inproceedings{rao-etal-2023-length,
title = "Length-Aware {NMT} and Adaptive Duration for Automatic Dubbing",
author = "Rao, Zhiqiang and
Shang, Hengchao and
Yang, Jinlong and
Wei, Daimeng and
Li, Zongyao and
Guo, Jiaxin and
Li, Shaojun and
Yu, Zhengzhe and
Wu, Zhanglin and
Xie, Yuhao and
Wei, Bin and
Zheng, Jiawei and
Lei, Lizhi and
Yang, Hao",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.9",
doi = "10.18653/v1/2023.iwslt-1.9",
pages = "138--143",
abstract = "This paper presents the submission of Huawei Translation Services Center for the IWSLT 2023 dubbing task in the unconstrained setting. The proposed solution consists of a Transformer-based machine translation model and a phoneme duration predictor. The Transformer is deep and multiple target-to-source length-ratio class labels are used to control target lengths. The variation predictor in FastSpeech2 is utilized to predict phoneme durations. To optimize the isochrony in dubbing, re-ranking and scaling are performed. The source audio duration is used as a reference to re-rank the translations of different length-ratio labels, and the one with minimum time deviation is preferred. Additionally, the phoneme duration outputs are scaled within a defined threshold to narrow the duration gap with the source audio.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-etal-2023-length">
<titleInfo>
<title>Length-Aware NMT and Adaptive Duration for Automatic Dubbing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaojun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengzhe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhao</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the submission of Huawei Translation Services Center for the IWSLT 2023 dubbing task in the unconstrained setting. The proposed solution consists of a Transformer-based machine translation model and a phoneme duration predictor. The Transformer is deep and multiple target-to-source length-ratio class labels are used to control target lengths. The variation predictor in FastSpeech2 is utilized to predict phoneme durations. To optimize the isochrony in dubbing, re-ranking and scaling are performed. The source audio duration is used as a reference to re-rank the translations of different length-ratio labels, and the one with minimum time deviation is preferred. Additionally, the phoneme duration outputs are scaled within a defined threshold to narrow the duration gap with the source audio.</abstract>
<identifier type="citekey">rao-etal-2023-length</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.9</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.9</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>138</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Length-Aware NMT and Adaptive Duration for Automatic Dubbing
%A Rao, Zhiqiang
%A Shang, Hengchao
%A Yang, Jinlong
%A Wei, Daimeng
%A Li, Zongyao
%A Guo, Jiaxin
%A Li, Shaojun
%A Yu, Zhengzhe
%A Wu, Zhanglin
%A Xie, Yuhao
%A Wei, Bin
%A Zheng, Jiawei
%A Lei, Lizhi
%A Yang, Hao
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F rao-etal-2023-length
%X This paper presents the submission of Huawei Translation Services Center for the IWSLT 2023 dubbing task in the unconstrained setting. The proposed solution consists of a Transformer-based machine translation model and a phoneme duration predictor. The Transformer is deep and multiple target-to-source length-ratio class labels are used to control target lengths. The variation predictor in FastSpeech2 is utilized to predict phoneme durations. To optimize the isochrony in dubbing, re-ranking and scaling are performed. The source audio duration is used as a reference to re-rank the translations of different length-ratio labels, and the one with minimum time deviation is preferred. Additionally, the phoneme duration outputs are scaled within a defined threshold to narrow the duration gap with the source audio.
%R 10.18653/v1/2023.iwslt-1.9
%U https://aclanthology.org/2023.iwslt-1.9
%U https://doi.org/10.18653/v1/2023.iwslt-1.9
%P 138-143
Markdown (Informal)
[Length-Aware NMT and Adaptive Duration for Automatic Dubbing](https://aclanthology.org/2023.iwslt-1.9) (Rao et al., IWSLT 2023)
ACL
- Zhiqiang Rao, Hengchao Shang, Jinlong Yang, Daimeng Wei, Zongyao Li, Jiaxin Guo, Shaojun Li, Zhengzhe Yu, Zhanglin Wu, Yuhao Xie, Bin Wei, Jiawei Zheng, Lizhi Lei, and Hao Yang. 2023. Length-Aware NMT and Adaptive Duration for Automatic Dubbing. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 138–143, Toronto, Canada (in-person and online). Association for Computational Linguistics.