@inproceedings{ranjbar-kalahroodi-etal-2026-parsvoice,
title = "{P}ars{V}oice: A Large-Scale Multi-Speaker {P}ersian Speech Corpus for Text-to-Speech Synthesis",
author = "Ranjbar Kalahroodi, Mohammad Javad and
Shakery, Azadeh and
Faili, Heshaam",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2458/",
pages = "55804--55819",
ISBN = "979-8-89176-459-0",
abstract = "Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, and a multi-dimensional quality assessment that covers both audio and Persian-specific text properties. The resulting release contains a 2,200-hour TTS-ready subset with 1.36 million aligned segments from 1,815 automatically inferred speaker IDs, making it more than 25 times larger than the largest previously available open Persian TTS dataset. To validate the corpus, we fine-tune XTTSv2, a zero-shot multilingual TTS model that operates directly on raw Persian text without phoneme representations. The resulting model achieves a naturalness MOS of 3.6/5 and a speaker-similarity MOS of 4.0/5. ParsVoice, its metadata, and the corpus-construction pipeline are publicly available on Hugging Face and GitHub, supporting reproducible research on Persian speech synthesis and low-resource speech-language technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranjbar-kalahroodi-etal-2026-parsvoice">
<titleInfo>
<title>ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Javad</namePart>
<namePart type="family">Ranjbar Kalahroodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azadeh</namePart>
<namePart type="family">Shakery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heshaam</namePart>
<namePart type="family">Faili</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, and a multi-dimensional quality assessment that covers both audio and Persian-specific text properties. The resulting release contains a 2,200-hour TTS-ready subset with 1.36 million aligned segments from 1,815 automatically inferred speaker IDs, making it more than 25 times larger than the largest previously available open Persian TTS dataset. To validate the corpus, we fine-tune XTTSv2, a zero-shot multilingual TTS model that operates directly on raw Persian text without phoneme representations. The resulting model achieves a naturalness MOS of 3.6/5 and a speaker-similarity MOS of 4.0/5. ParsVoice, its metadata, and the corpus-construction pipeline are publicly available on Hugging Face and GitHub, supporting reproducible research on Persian speech synthesis and low-resource speech-language technologies.</abstract>
<identifier type="citekey">ranjbar-kalahroodi-etal-2026-parsvoice</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2458/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>55804</start>
<end>55819</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis
%A Ranjbar Kalahroodi, Mohammad Javad
%A Shakery, Azadeh
%A Faili, Heshaam
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F ranjbar-kalahroodi-etal-2026-parsvoice
%X Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, and a multi-dimensional quality assessment that covers both audio and Persian-specific text properties. The resulting release contains a 2,200-hour TTS-ready subset with 1.36 million aligned segments from 1,815 automatically inferred speaker IDs, making it more than 25 times larger than the largest previously available open Persian TTS dataset. To validate the corpus, we fine-tune XTTSv2, a zero-shot multilingual TTS model that operates directly on raw Persian text without phoneme representations. The resulting model achieves a naturalness MOS of 3.6/5 and a speaker-similarity MOS of 4.0/5. ParsVoice, its metadata, and the corpus-construction pipeline are publicly available on Hugging Face and GitHub, supporting reproducible research on Persian speech synthesis and low-resource speech-language technologies.
%U https://aclanthology.org/2026.emnlp-main.2458/
%P 55804-55819
Markdown (Informal)
[ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis](https://aclanthology.org/2026.emnlp-main.2458/) (Ranjbar Kalahroodi et al., EMNLP 2026)
ACL