@inproceedings{dhar-etal-2025-ju,
title = "{JU}-{CSE}-{NLP}{'}s Cascaded Speech to Text Translation Systems for {IWSLT} 2025 in {I}ndic Track",
author = "Dhar, Debjit and
Lahiri, Soham and
Mondal, Tapabrata 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-1.18/",
doi = "10.18653/v1/2025.iwslt-1.18",
pages = "201--205",
ISBN = "979-8-89176-272-5",
abstract = "This paper presents the submission of the Jadavpur University Computer Science and Engineering Natural Language Processing (JU-CSENLP) Laboratory to the International Conference on Spoken Language Translation (IWSLT) 2025 Indic track, addressing the speech-to-text translation task in both English-to-Indic (Bengali, Hindi, Tamil) and Indic-to-English directions. To tackle the challenges posed by low resource Indian languages, we adopt a cascaded approach leveraging state-of-the-art pre-trained models. For English-to-Indic translation, we utilize OpenAI{'}s Whisper model for Automatic Speech Recognition (ASR), followed by the Meta{'}s No Language Left Behind (NLLB)-200-distilled-600M model finetuned for Machine Translation (MT). For the reverse direction, we employ the AI4Bharat{'}s IndicConformer model for ASR and IndicTrans2 finetuned for MT. Our models are fine-tuned on the provided benchmark dataset to better handle the linguistic diversity and domain-specific variations inherent in the data. Evaluation results demonstrate that our cascaded systems achieve competitive performance, with notable BLEU and chrF++ scores across all language pairs. Our findings highlight the effectiveness of combining robust ASR and MT components in a cascaded pipeline, particularly for low-resource and morphologically rich Indian languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhar-etal-2025-ju">
<titleInfo>
<title>JU-CSE-NLP’s Cascaded Speech to Text Translation Systems for IWSLT 2025 in Indic Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debjit</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tapabrata</namePart>
<namePart type="family">Mondal</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>This paper presents the submission of the Jadavpur University Computer Science and Engineering Natural Language Processing (JU-CSENLP) Laboratory to the International Conference on Spoken Language Translation (IWSLT) 2025 Indic track, addressing the speech-to-text translation task in both English-to-Indic (Bengali, Hindi, Tamil) and Indic-to-English directions. To tackle the challenges posed by low resource Indian languages, we adopt a cascaded approach leveraging state-of-the-art pre-trained models. For English-to-Indic translation, we utilize OpenAI’s Whisper model for Automatic Speech Recognition (ASR), followed by the Meta’s No Language Left Behind (NLLB)-200-distilled-600M model finetuned for Machine Translation (MT). For the reverse direction, we employ the AI4Bharat’s IndicConformer model for ASR and IndicTrans2 finetuned for MT. Our models are fine-tuned on the provided benchmark dataset to better handle the linguistic diversity and domain-specific variations inherent in the data. Evaluation results demonstrate that our cascaded systems achieve competitive performance, with notable BLEU and chrF++ scores across all language pairs. Our findings highlight the effectiveness of combining robust ASR and MT components in a cascaded pipeline, particularly for low-resource and morphologically rich Indian languages.</abstract>
<identifier type="citekey">dhar-etal-2025-ju</identifier>
<identifier type="doi">10.18653/v1/2025.iwslt-1.18</identifier>
<location>
<url>https://aclanthology.org/2025.iwslt-1.18/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>201</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JU-CSE-NLP’s Cascaded Speech to Text Translation Systems for IWSLT 2025 in Indic Track
%A Dhar, Debjit
%A Lahiri, Soham
%A Mondal, Tapabrata
%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 dhar-etal-2025-ju
%X This paper presents the submission of the Jadavpur University Computer Science and Engineering Natural Language Processing (JU-CSENLP) Laboratory to the International Conference on Spoken Language Translation (IWSLT) 2025 Indic track, addressing the speech-to-text translation task in both English-to-Indic (Bengali, Hindi, Tamil) and Indic-to-English directions. To tackle the challenges posed by low resource Indian languages, we adopt a cascaded approach leveraging state-of-the-art pre-trained models. For English-to-Indic translation, we utilize OpenAI’s Whisper model for Automatic Speech Recognition (ASR), followed by the Meta’s No Language Left Behind (NLLB)-200-distilled-600M model finetuned for Machine Translation (MT). For the reverse direction, we employ the AI4Bharat’s IndicConformer model for ASR and IndicTrans2 finetuned for MT. Our models are fine-tuned on the provided benchmark dataset to better handle the linguistic diversity and domain-specific variations inherent in the data. Evaluation results demonstrate that our cascaded systems achieve competitive performance, with notable BLEU and chrF++ scores across all language pairs. Our findings highlight the effectiveness of combining robust ASR and MT components in a cascaded pipeline, particularly for low-resource and morphologically rich Indian languages.
%R 10.18653/v1/2025.iwslt-1.18
%U https://aclanthology.org/2025.iwslt-1.18/
%U https://doi.org/10.18653/v1/2025.iwslt-1.18
%P 201-205
Markdown (Informal)
[JU-CSE-NLP’s Cascaded Speech to Text Translation Systems for IWSLT 2025 in Indic Track](https://aclanthology.org/2025.iwslt-1.18/) (Dhar et al., IWSLT 2025)
ACL