@inproceedings{guo-etal-2022-xiaomi,
title = "The Xiaomi Text-to-Text Simultaneous Speech Translation System for {IWSLT} 2022",
author = "Guo, Bao and
Liu, Mengge and
Zhang, Wen and
Chen, Hexuan and
Mu, Chang and
Li, Xiang and
Cui, Jianwei and
Wang, Bin and
Guo, Yuhang",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Costa-juss{\`a}, Marta",
booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.iwslt-1.17",
doi = "10.18653/v1/2022.iwslt-1.17",
pages = "216--224",
abstract = "This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track. Our system is built based on the Transformer model with novel techniques borrowed from our recent research work. For the data filtering, language-model-based and rule-based methods are conducted to filter the data to obtain high-quality bilingual parallel corpora. We also strengthen our system with some dominating techniques related to data augmentation, such as knowledge distillation, tagged back-translation, and iterative back-translation. We also incorporate novel training techniques such as R-drop, deep model, and large batch training which have been shown to be beneficial to the naive Transformer model. In the SST scenario, several variations of $exttt{wait-k}$ strategies are explored. Furthermore, in terms of robustness, both data-based and model-based ways are used to reduce the sensitivity of our system to Automatic Speech Recognition (ASR) outputs. We finally design some inference algorithms and use the adaptive-ensemble method based on multiple model variants to further improve the performance of the system. Compared with strong baselines, fusing all techniques can improve our system by 2 extasciitilde3 BLEU scores under different latency regimes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2022-xiaomi">
<titleInfo>
<title>The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengge</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hexuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Mu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianwei</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)</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">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track. Our system is built based on the Transformer model with novel techniques borrowed from our recent research work. For the data filtering, language-model-based and rule-based methods are conducted to filter the data to obtain high-quality bilingual parallel corpora. We also strengthen our system with some dominating techniques related to data augmentation, such as knowledge distillation, tagged back-translation, and iterative back-translation. We also incorporate novel training techniques such as R-drop, deep model, and large batch training which have been shown to be beneficial to the naive Transformer model. In the SST scenario, several variations of extttwait-k strategies are explored. Furthermore, in terms of robustness, both data-based and model-based ways are used to reduce the sensitivity of our system to Automatic Speech Recognition (ASR) outputs. We finally design some inference algorithms and use the adaptive-ensemble method based on multiple model variants to further improve the performance of the system. Compared with strong baselines, fusing all techniques can improve our system by 2 extasciitilde3 BLEU scores under different latency regimes.</abstract>
<identifier type="citekey">guo-etal-2022-xiaomi</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.17</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.17</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>216</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022
%A Guo, Bao
%A Liu, Mengge
%A Zhang, Wen
%A Chen, Hexuan
%A Mu, Chang
%A Li, Xiang
%A Cui, Jianwei
%A Wang, Bin
%A Guo, Yuhang
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Costa-jussà, Marta
%S Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland (in-person and online)
%F guo-etal-2022-xiaomi
%X This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track. Our system is built based on the Transformer model with novel techniques borrowed from our recent research work. For the data filtering, language-model-based and rule-based methods are conducted to filter the data to obtain high-quality bilingual parallel corpora. We also strengthen our system with some dominating techniques related to data augmentation, such as knowledge distillation, tagged back-translation, and iterative back-translation. We also incorporate novel training techniques such as R-drop, deep model, and large batch training which have been shown to be beneficial to the naive Transformer model. In the SST scenario, several variations of extttwait-k strategies are explored. Furthermore, in terms of robustness, both data-based and model-based ways are used to reduce the sensitivity of our system to Automatic Speech Recognition (ASR) outputs. We finally design some inference algorithms and use the adaptive-ensemble method based on multiple model variants to further improve the performance of the system. Compared with strong baselines, fusing all techniques can improve our system by 2 extasciitilde3 BLEU scores under different latency regimes.
%R 10.18653/v1/2022.iwslt-1.17
%U https://aclanthology.org/2022.iwslt-1.17
%U https://doi.org/10.18653/v1/2022.iwslt-1.17
%P 216-224
Markdown (Informal)
[The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022](https://aclanthology.org/2022.iwslt-1.17) (Guo et al., IWSLT 2022)
ACL
- Bao Guo, Mengge Liu, Wen Zhang, Hexuan Chen, Chang Mu, Xiang Li, Jianwei Cui, Bin Wang, and Yuhang Guo. 2022. The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 216–224, Dublin, Ireland (in-person and online). Association for Computational Linguistics.