<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-song-2024-nicts">
    <titleInfo>
        <title>NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raj</namePart>
        <namePart type="family">Dabre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haiyue</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</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">Bangkok, Thailand (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents the NICT’s submission for the IWSLT 2024 Indic track, focusing on three speech-to-text (ST) translation directions: English to Hindi, Bengali, and Tamil. We aim to enhance translation quality in this low-resource scenario by integrating state-of-the-art pre-trained automated speech recognition (ASR) and text-to-text machine translation (MT) models. Our cascade system incorporates a Whisper model fine-tuned for ASR and an IndicTrans2 model fine-tuned for MT. Additionally, we propose an end-to-end system that combines a Whisper model for speech-to-text conversion with knowledge distilled from an IndicTrans2 MT model. We first fine-tune the IndicTrans2 model to generate pseudo data in Indic languages. This pseudo data, along with the original English speech data, is then used to fine-tune the Whisper model. Experimental results show that the cascaded system achieved a BLEU score of 51.0, outperforming the end-to-end model, which scored 19.1 BLEU. Moreover, the analysis indicates that applying knowledge distillation from the IndicTrans2 model to the end-to-end ST model improves the translation quality by about 0.7 BLEU.</abstract>
    <identifier type="citekey">dabre-song-2024-nicts</identifier>
    <location>
        <url>https://aclanthology.org/2024.iwslt-1.3</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>17</start>
            <end>22</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task
%A Dabre, Raj
%A Song, Haiyue
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F dabre-song-2024-nicts
%X This paper presents the NICT’s submission for the IWSLT 2024 Indic track, focusing on three speech-to-text (ST) translation directions: English to Hindi, Bengali, and Tamil. We aim to enhance translation quality in this low-resource scenario by integrating state-of-the-art pre-trained automated speech recognition (ASR) and text-to-text machine translation (MT) models. Our cascade system incorporates a Whisper model fine-tuned for ASR and an IndicTrans2 model fine-tuned for MT. Additionally, we propose an end-to-end system that combines a Whisper model for speech-to-text conversion with knowledge distilled from an IndicTrans2 MT model. We first fine-tune the IndicTrans2 model to generate pseudo data in Indic languages. This pseudo data, along with the original English speech data, is then used to fine-tune the Whisper model. Experimental results show that the cascaded system achieved a BLEU score of 51.0, outperforming the end-to-end model, which scored 19.1 BLEU. Moreover, the analysis indicates that applying knowledge distillation from the IndicTrans2 model to the end-to-end ST model improves the translation quality by about 0.7 BLEU.
%U https://aclanthology.org/2024.iwslt-1.3
%P 17-22

Markdown (Informal)

[NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task](https://aclanthology.org/2024.iwslt-1.3) (Dabre & Song, IWSLT 2024)

• NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task (Dabre & Song, IWSLT 2024)

ACL

• Raj Dabre and Haiyue Song. 2024. NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 17–22, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.