<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sewunetie-etal-2026-amhtts">
    <titleInfo>
        <title>AmhTTS: A Low-Resource Amharic Text-to-Speech System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Walelign</namePart>
        <namePart type="given">Tewabe</namePart>
        <namePart type="family">Sewunetie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rahel</namePart>
        <namePart type="given">Mekonen</namePart>
        <namePart type="family">Tamiru</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Israel</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Gebru</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 10th Widening NLP Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chen</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Allaway</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Meryem</namePart>
            <namePart type="family">M’hamdi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peerat</namePart>
            <namePart type="family">Limkonchotiwat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="given">He</namePart>
            <namePart type="family">Bai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yinqiao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-472-9</identifier>
    </relatedItem>
    <abstract>The scarcity of high-quality, phonetically diverse datasets for low-resource languages like Amharic remains a significant barrier to high-fidelity speech synthesis. We present AmhTTS, the first open, natively evaluated Amharic text-to-speech system, developed by fine-tuning SpeechT5 on a curated 25-hour, single-speaker Amharic corpus paired with a HiFi-GAN vocoder. Unlike Meta MMS, the only other publicly available Amharic TTS system, which requires Latin script transliteration and reports no Amharic-specific evaluation, AmhTTS operates natively on Ethiopic script and is the first system to report human MOS scores on Amharic speech synthesis. To address the orthographic complexities of the Ethiopic script, we implement a three-stage text normalisation pipeline covering homophone unification, Ge’ez numeral expansion, and Amharic punctuation handling. System quality is assessed through a rigorous human evaluation via a purpose-built web platform, involving 28 native Amharic-speaking voluntary evaluators who rated 35 linguistically motivated samples across four domains: phonetic coverage (ejectives and labialized consonants), gemination and prosody, numeral and date reading, and conversational fluency. Results yield an overall naturalness MOS of 3.71 and intelligibility MOS of 4.02 on a 5-point scale, demonstrating that the rich pre-trained representations of SpeechT5 transfer effectively to a low-resource language with only 25 hours of data a fraction of the 460 hours used in the original English fine-tuning. While the system achieves high phonetic accuracy (MOS: 4.22/4.36), numeral synthesis and gemination modeling remain areas for future improvement. Given the demonstrated community demand for accessibility tools, we publicly release our fine-tuned model weights, the AmhTTS corpus, and evaluation data to advance low-resource TTS research. Our web application is currently active, serving users at multiple university disability centers in Ethiopia.</abstract>
    <identifier type="citekey">sewunetie-etal-2026-amhtts</identifier>
    <location>
        <url>https://aclanthology.org/2026.winlp-main.7/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>68</start>
            <end>76</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AmhTTS: A Low-Resource Amharic Text-to-Speech System
%A Sewunetie, Walelign Tewabe
%A Tamiru, Rahel Mekonen
%A Gebru, Israel D.
%Y Zhang, Chen
%Y Allaway, Emily
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.Y.S.S., Santosh
%Y Thapa, Surendrabikram
%Y Li, Yinqiao
%S Proceedings of the 10th Widening NLP Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-472-9
%F sewunetie-etal-2026-amhtts
%X The scarcity of high-quality, phonetically diverse datasets for low-resource languages like Amharic remains a significant barrier to high-fidelity speech synthesis. We present AmhTTS, the first open, natively evaluated Amharic text-to-speech system, developed by fine-tuning SpeechT5 on a curated 25-hour, single-speaker Amharic corpus paired with a HiFi-GAN vocoder. Unlike Meta MMS, the only other publicly available Amharic TTS system, which requires Latin script transliteration and reports no Amharic-specific evaluation, AmhTTS operates natively on Ethiopic script and is the first system to report human MOS scores on Amharic speech synthesis. To address the orthographic complexities of the Ethiopic script, we implement a three-stage text normalisation pipeline covering homophone unification, Ge’ez numeral expansion, and Amharic punctuation handling. System quality is assessed through a rigorous human evaluation via a purpose-built web platform, involving 28 native Amharic-speaking voluntary evaluators who rated 35 linguistically motivated samples across four domains: phonetic coverage (ejectives and labialized consonants), gemination and prosody, numeral and date reading, and conversational fluency. Results yield an overall naturalness MOS of 3.71 and intelligibility MOS of 4.02 on a 5-point scale, demonstrating that the rich pre-trained representations of SpeechT5 transfer effectively to a low-resource language with only 25 hours of data a fraction of the 460 hours used in the original English fine-tuning. While the system achieves high phonetic accuracy (MOS: 4.22/4.36), numeral synthesis and gemination modeling remain areas for future improvement. Given the demonstrated community demand for accessibility tools, we publicly release our fine-tuned model weights, the AmhTTS corpus, and evaluation data to advance low-resource TTS research. Our web application is currently active, serving users at multiple university disability centers in Ethiopia.
%U https://aclanthology.org/2026.winlp-main.7/
%P 68-76

Markdown (Informal)

[AmhTTS: A Low-Resource Amharic Text-to-Speech System](https://aclanthology.org/2026.winlp-main.7/) (Sewunetie et al., WiNLP 2026)

• AmhTTS: A Low-Resource Amharic Text-to-Speech System (Sewunetie et al., WiNLP 2026)

ACL

• Walelign Tewabe Sewunetie, Rahel Mekonen Tamiru, and Israel D. Gebru. 2026. AmhTTS: A Low-Resource Amharic Text-to-Speech System. In Proceedings of the 10th Widening NLP Workshop, pages 68–76, Budapest, Hungary. Association for Computational Linguistics.