@inproceedings{das-etal-2025-iwslt,
title = "{IWSLT} 2025 {I}ndic Track System Description Paper: Speech-to-Text Translation from Low-Resource {I}ndian Languages ({B}engali and {T}amil) to {E}nglish",
author = "Das, Sayan and
Chaudhuri, Soham and
Saha, Dipanjan and
Das, Dipankar and
Bandyopadhyay, Sivaji",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Anastasopoulos, Antonis",
booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwslt-1.23/",
doi = "10.18653/v1/2025.iwslt-1.23",
pages = "245--251",
ISBN = "979-8-89176-272-5",
abstract = "Multi-language Speech-to-Text Translation (ST) plays a crucial role in breaking linguistic barriers, particularly in multilingual regions like India. This paper focuses on building a robust ST system for low resource Indian languages, with a special emphasis on Bengali and Tamil. These languages represent the Indo-Aryan and Dravidian families, respectively. The dataset used in this work comprises spoken content from TED Talks and conferences, paired with transcriptions in English and their translations in Bengali and Tamil. Our work specifically addresses the translation of Bengali and Tamil speech to English text, a critical area given the scarcity of annotated speech data. To enhance translation quality and model robustness, we leverage cross-lingual resources and word level translation strategies. The ultimate goal is to develop an end-to-end ST model capable of real-world deployment for under represented languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2025-iwslt">
<titleInfo>
<title>IWSLT 2025 Indic Track System Description Paper: Speech-to-Text Translation from Low-Resource Indian Languages (Bengali and Tamil) to English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sayan</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Chaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</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">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-272-5</identifier>
</relatedItem>
<abstract>Multi-language Speech-to-Text Translation (ST) plays a crucial role in breaking linguistic barriers, particularly in multilingual regions like India. This paper focuses on building a robust ST system for low resource Indian languages, with a special emphasis on Bengali and Tamil. These languages represent the Indo-Aryan and Dravidian families, respectively. The dataset used in this work comprises spoken content from TED Talks and conferences, paired with transcriptions in English and their translations in Bengali and Tamil. Our work specifically addresses the translation of Bengali and Tamil speech to English text, a critical area given the scarcity of annotated speech data. To enhance translation quality and model robustness, we leverage cross-lingual resources and word level translation strategies. The ultimate goal is to develop an end-to-end ST model capable of real-world deployment for under represented languages.</abstract>
<identifier type="citekey">das-etal-2025-iwslt</identifier>
<identifier type="doi">10.18653/v1/2025.iwslt-1.23</identifier>
<location>
<url>https://aclanthology.org/2025.iwslt-1.23/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>245</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IWSLT 2025 Indic Track System Description Paper: Speech-to-Text Translation from Low-Resource Indian Languages (Bengali and Tamil) to English
%A Das, Sayan
%A Chaudhuri, Soham
%A Saha, Dipanjan
%A Das, Dipankar
%A Bandyopadhyay, Sivaji
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F das-etal-2025-iwslt
%X Multi-language Speech-to-Text Translation (ST) plays a crucial role in breaking linguistic barriers, particularly in multilingual regions like India. This paper focuses on building a robust ST system for low resource Indian languages, with a special emphasis on Bengali and Tamil. These languages represent the Indo-Aryan and Dravidian families, respectively. The dataset used in this work comprises spoken content from TED Talks and conferences, paired with transcriptions in English and their translations in Bengali and Tamil. Our work specifically addresses the translation of Bengali and Tamil speech to English text, a critical area given the scarcity of annotated speech data. To enhance translation quality and model robustness, we leverage cross-lingual resources and word level translation strategies. The ultimate goal is to develop an end-to-end ST model capable of real-world deployment for under represented languages.
%R 10.18653/v1/2025.iwslt-1.23
%U https://aclanthology.org/2025.iwslt-1.23/
%U https://doi.org/10.18653/v1/2025.iwslt-1.23
%P 245-251
Markdown (Informal)
[IWSLT 2025 Indic Track System Description Paper: Speech-to-Text Translation from Low-Resource Indian Languages (Bengali and Tamil) to English](https://aclanthology.org/2025.iwslt-1.23/) (Das et al., IWSLT 2025)
ACL