@inproceedings{radhakrishnan-etal-2023-sri,
title = "{SRI}-{B}{'}s Systems for {IWSLT} 2023 Dialectal and Low-resource Track: {M}arathi-{H}indi Speech Translation",
author = "Radhakrishnan, Balaji and
Agrawal, Saurabh and
Prakash Gohil, Raj and
Praveen, Kiran and
Vinay Dhopeshwarkar, Advait and
Pandey, Abhishek",
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-1.43",
doi = "10.18653/v1/2023.iwslt-1.43",
pages = "449--454",
abstract = "This paper describes the speech translation systems SRI-B developed for the IWSLT 2023 Evaluation Campaign Dialectal and Low-resource track: Marathi-Hindi Speech Translation. We propose systems for both the constrained (systems are trained only on the datasets provided by the organizers) and the unconstrained conditions (systems can be trained with any resource). For both the conditions, we build end-to-end speech translation networks comprising of a conformer encoder and a transformer decoder. Under both the conditions, we leverage Marathi Automatic Speech Recognition (ASR) data to pre-train the encoder and subsequently train the entire model on the speech translation data. Our results demonstrate that pre-training the encoder with ASR data is a key step in significantly improving the speech translation performance. We also show that conformer encoders are inherently superior to its transformer counterparts for speech translation tasks. Our primary submissions achieved a BLEU{\%} score of 31.2 on the constrained condition and 32.4 on the unconstrained condition. We secured the top position in the constrained condition and second position in the unconstrained condition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="radhakrishnan-etal-2023-sri">
<titleInfo>
<title>SRI-B’s Systems for IWSLT 2023 Dialectal and Low-resource Track: Marathi-Hindi Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Balaji</namePart>
<namePart type="family">Radhakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Prakash Gohil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiran</namePart>
<namePart type="family">Praveen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Advait</namePart>
<namePart type="family">Vinay Dhopeshwarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Pandey</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 describes the speech translation systems SRI-B developed for the IWSLT 2023 Evaluation Campaign Dialectal and Low-resource track: Marathi-Hindi Speech Translation. We propose systems for both the constrained (systems are trained only on the datasets provided by the organizers) and the unconstrained conditions (systems can be trained with any resource). For both the conditions, we build end-to-end speech translation networks comprising of a conformer encoder and a transformer decoder. Under both the conditions, we leverage Marathi Automatic Speech Recognition (ASR) data to pre-train the encoder and subsequently train the entire model on the speech translation data. Our results demonstrate that pre-training the encoder with ASR data is a key step in significantly improving the speech translation performance. We also show that conformer encoders are inherently superior to its transformer counterparts for speech translation tasks. Our primary submissions achieved a BLEU% score of 31.2 on the constrained condition and 32.4 on the unconstrained condition. We secured the top position in the constrained condition and second position in the unconstrained condition.</abstract>
<identifier type="citekey">radhakrishnan-etal-2023-sri</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.43</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.43</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>449</start>
<end>454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SRI-B’s Systems for IWSLT 2023 Dialectal and Low-resource Track: Marathi-Hindi Speech Translation
%A Radhakrishnan, Balaji
%A Agrawal, Saurabh
%A Prakash Gohil, Raj
%A Praveen, Kiran
%A Vinay Dhopeshwarkar, Advait
%A Pandey, Abhishek
%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 radhakrishnan-etal-2023-sri
%X This paper describes the speech translation systems SRI-B developed for the IWSLT 2023 Evaluation Campaign Dialectal and Low-resource track: Marathi-Hindi Speech Translation. We propose systems for both the constrained (systems are trained only on the datasets provided by the organizers) and the unconstrained conditions (systems can be trained with any resource). For both the conditions, we build end-to-end speech translation networks comprising of a conformer encoder and a transformer decoder. Under both the conditions, we leverage Marathi Automatic Speech Recognition (ASR) data to pre-train the encoder and subsequently train the entire model on the speech translation data. Our results demonstrate that pre-training the encoder with ASR data is a key step in significantly improving the speech translation performance. We also show that conformer encoders are inherently superior to its transformer counterparts for speech translation tasks. Our primary submissions achieved a BLEU% score of 31.2 on the constrained condition and 32.4 on the unconstrained condition. We secured the top position in the constrained condition and second position in the unconstrained condition.
%R 10.18653/v1/2023.iwslt-1.43
%U https://aclanthology.org/2023.iwslt-1.43
%U https://doi.org/10.18653/v1/2023.iwslt-1.43
%P 449-454
Markdown (Informal)
[SRI-B’s Systems for IWSLT 2023 Dialectal and Low-resource Track: Marathi-Hindi Speech Translation](https://aclanthology.org/2023.iwslt-1.43) (Radhakrishnan et al., IWSLT 2023)
ACL