<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khamis-ahmed-2026-llm">
    <titleInfo>
        <title>LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Khamis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hesham</namePart>
        <namePart type="given">Ali</namePart>
        <namePart type="family">Ahmed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources con- centrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic— the most widely understood Arabic dialect— severely under-resourced. We address this gap by introducing NileTTS: 38 hours of tran- scribed speech from two speakers across di- verse domains including medical, sales, and general conversations. We construct this dataset using a novel synthetic pipeline: large language models (LLM) generate Egyptian Arabic content, which is then converted to natu- ral speech using audio synthesis tools, followed by automatic transcription and speaker diariza- tion with manual quality verification. We fine- tune XTTS v2, a state-of-the-art multilingual TTS model, on our dataset and evaluate against the baseline model trained on other Arabic dialects. Our contributions include: (1) the first publicly available Egyptian Arabic TTS dataset, (2) a reproducible synthetic data gen- eration pipeline for dialectal TTS, and (3) an open-source fine-tuned model. All resources are released to advance Egyptian Arabic speech synthesis research.</abstract>
    <identifier type="citekey">khamis-ahmed-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.abjadnlp-1.6/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>47</start>
            <end>54</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models
%A Khamis, Ahmed
%A Ahmed, Hesham Ali
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F khamis-ahmed-2026-llm
%X Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources con- centrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic— the most widely understood Arabic dialect— severely under-resourced. We address this gap by introducing NileTTS: 38 hours of tran- scribed speech from two speakers across di- verse domains including medical, sales, and general conversations. We construct this dataset using a novel synthetic pipeline: large language models (LLM) generate Egyptian Arabic content, which is then converted to natu- ral speech using audio synthesis tools, followed by automatic transcription and speaker diariza- tion with manual quality verification. We fine- tune XTTS v2, a state-of-the-art multilingual TTS model, on our dataset and evaluate against the baseline model trained on other Arabic dialects. Our contributions include: (1) the first publicly available Egyptian Arabic TTS dataset, (2) a reproducible synthetic data gen- eration pipeline for dialectal TTS, and (3) an open-source fine-tuned model. All resources are released to advance Egyptian Arabic speech synthesis research.
%U https://aclanthology.org/2026.abjadnlp-1.6/
%P 47-54

Markdown (Informal)

[LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models](https://aclanthology.org/2026.abjadnlp-1.6/) (Khamis & Ahmed, AbjadNLP 2026)

• LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models (Khamis & Ahmed, AbjadNLP 2026)

ACL

• Ahmed Khamis and Hesham Ali Ahmed. 2026. LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 47–54, Rabat, Morocco. Association for Computational Linguistics.