<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gopinath-etal-2026-imasc">
    <titleInfo>
        <title>IMaSC: A Malayalam Speech Corpus for High-Quality Text-to-Speech Synthesis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Deepa</namePart>
        <namePart type="given">P</namePart>
        <namePart type="family">Gopinath</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thennal</namePart>
        <namePart type="family">D K</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vrinda</namePart>
        <namePart type="given">V</namePart>
        <namePart type="family">Nair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Swaraj</namePart>
        <namePart type="given">K</namePart>
        <namePart type="family">S</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sachin</namePart>
        <namePart type="family">G</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high-quality audio-text sentence pairs for training. Malayalam, the official language of the Indian state of Kerala and spoken by 35+ million people, is a low-resource language in terms of available corpora for TTS systems. In this paper, we present IMaSC, a Malayalam text and speech corpora containing 49 hours and 37 minutes of recorded speech. With 8 speakers and a total of 34,473 text-audio pairs, IMaSC is larger than every other publicly available alternative. We evaluated the database by using it to train TTS models for each speaker based on a modern deep learning architecture. With an average mean opinion score of 4.50, we find that the synthesized speech of our model is close to human quality.</abstract>
    <identifier type="citekey">gopinath-etal-2026-imasc</identifier>
    <identifier type="doi">10.63317/39kfsuabkvgh</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.465/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>5864</start>
            <end>5872</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T IMaSC: A Malayalam Speech Corpus for High-Quality Text-to-Speech Synthesis
%A Gopinath, Deepa P.
%A D K, Thennal
%A Nair, Vrinda V.
%A S, Swaraj K.
%A G, Sachin
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F gopinath-etal-2026-imasc
%X Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high-quality audio-text sentence pairs for training. Malayalam, the official language of the Indian state of Kerala and spoken by 35+ million people, is a low-resource language in terms of available corpora for TTS systems. In this paper, we present IMaSC, a Malayalam text and speech corpora containing 49 hours and 37 minutes of recorded speech. With 8 speakers and a total of 34,473 text-audio pairs, IMaSC is larger than every other publicly available alternative. We evaluated the database by using it to train TTS models for each speaker based on a modern deep learning architecture. With an average mean opinion score of 4.50, we find that the synthesized speech of our model is close to human quality.
%R 10.63317/39kfsuabkvgh
%U https://aclanthology.org/2026.lrec-1.465/
%U https://doi.org/10.63317/39kfsuabkvgh
%P 5864-5872

Markdown (Informal)

[IMaSC: A Malayalam Speech Corpus for High-Quality Text-to-Speech Synthesis](https://aclanthology.org/2026.lrec-1.465/) (Gopinath et al., LREC 2026)

• IMaSC: A Malayalam Speech Corpus for High-Quality Text-to-Speech Synthesis (Gopinath et al., LREC 2026)

ACL

• Deepa P. Gopinath, Thennal D K, Vrinda V. Nair, Swaraj K. S, and Sachin G. 2026. IMaSC: A Malayalam Speech Corpus for High-Quality Text-to-Speech Synthesis. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5864–5872, Palma de Mallorca, Spain. ELRA Language Resource Association.