@inproceedings{devauchelle-etal-2026-spinach,
title = "sp{INA}ch: A Diachronic Corpus of {F}rench Broadcast Speech Controlled for Speakers' Age and Gender",
author = "Devauchelle, Simon and
Doukhan, David and
Uro, Remi and
Ondel, Lucas and
Pelloin, Valentin and
Imbert-Br{\'e}g{\'e}g{\`e}re, Olympia and
Lefort, V{\'e}ronique and
Picard, K{\'e}vin and
Seignobos, Emeline and
Rilliard, Albert",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.459/",
doi = "10.63317/58hgwvgvkz6g",
pages = "5805--5820",
abstract = "We present spINAch, a large diachronic corpus of French speech from radio and television archives, balanced by speakers' gender, age (20-95 years old), and spanning 60 years from 1955 to 2015. The dataset includes over 320 hours of recordings from more than two thousand speakers. The methodology for building the corpus is described, focusing on the quality of collected samples in acoustic terms. The data were automatically transcribed and phonetically aligned to allow studies at a phonemic level. More than 3 million oral vowels have been analyzed to propose their fundamental frequency and formants. The corpus, available to the community for research purposes, is valuable for describing the evolution of Parisian French through the representation of gender and age. The presented analyses also demonstrate that the diachronic nature of the corpus allows the observation of various phonetic phenomena, such as the evolution of voice pitch over time (which does not differ by gender in our data) and the neutralization of the /a/-/ɑ/ opposition in Parisian French during this period."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devauchelle-etal-2026-spinach">
<titleInfo>
<title>spINAch: A Diachronic Corpus of French Broadcast Speech Controlled for Speakers’ Age and Gender</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Devauchelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Doukhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Remi</namePart>
<namePart type="family">Uro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Ondel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Pelloin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olympia</namePart>
<namePart type="family">Imbert-Brégégère</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Lefort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kévin</namePart>
<namePart type="family">Picard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emeline</namePart>
<namePart type="family">Seignobos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Rilliard</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>We present spINAch, a large diachronic corpus of French speech from radio and television archives, balanced by speakers’ gender, age (20-95 years old), and spanning 60 years from 1955 to 2015. The dataset includes over 320 hours of recordings from more than two thousand speakers. The methodology for building the corpus is described, focusing on the quality of collected samples in acoustic terms. The data were automatically transcribed and phonetically aligned to allow studies at a phonemic level. More than 3 million oral vowels have been analyzed to propose their fundamental frequency and formants. The corpus, available to the community for research purposes, is valuable for describing the evolution of Parisian French through the representation of gender and age. The presented analyses also demonstrate that the diachronic nature of the corpus allows the observation of various phonetic phenomena, such as the evolution of voice pitch over time (which does not differ by gender in our data) and the neutralization of the /a/-/ɑ/ opposition in Parisian French during this period.</abstract>
<identifier type="citekey">devauchelle-etal-2026-spinach</identifier>
<identifier type="doi">10.63317/58hgwvgvkz6g</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.459/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5805</start>
<end>5820</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T spINAch: A Diachronic Corpus of French Broadcast Speech Controlled for Speakers’ Age and Gender
%A Devauchelle, Simon
%A Doukhan, David
%A Uro, Remi
%A Ondel, Lucas
%A Pelloin, Valentin
%A Imbert-Brégégère, Olympia
%A Lefort, Véronique
%A Picard, Kévin
%A Seignobos, Emeline
%A Rilliard, Albert
%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 devauchelle-etal-2026-spinach
%X We present spINAch, a large diachronic corpus of French speech from radio and television archives, balanced by speakers’ gender, age (20-95 years old), and spanning 60 years from 1955 to 2015. The dataset includes over 320 hours of recordings from more than two thousand speakers. The methodology for building the corpus is described, focusing on the quality of collected samples in acoustic terms. The data were automatically transcribed and phonetically aligned to allow studies at a phonemic level. More than 3 million oral vowels have been analyzed to propose their fundamental frequency and formants. The corpus, available to the community for research purposes, is valuable for describing the evolution of Parisian French through the representation of gender and age. The presented analyses also demonstrate that the diachronic nature of the corpus allows the observation of various phonetic phenomena, such as the evolution of voice pitch over time (which does not differ by gender in our data) and the neutralization of the /a/-/ɑ/ opposition in Parisian French during this period.
%R 10.63317/58hgwvgvkz6g
%U https://aclanthology.org/2026.lrec-1.459/
%U https://doi.org/10.63317/58hgwvgvkz6g
%P 5805-5820
Markdown (Informal)
[spINAch: A Diachronic Corpus of French Broadcast Speech Controlled for Speakers’ Age and Gender](https://aclanthology.org/2026.lrec-1.459/) (Devauchelle et al., LREC 2026)
ACL
- Simon Devauchelle, David Doukhan, Remi Uro, Lucas Ondel, Valentin Pelloin, Olympia Imbert-Brégégère, Véronique Lefort, Kévin Picard, Emeline Seignobos, and Albert Rilliard. 2026. spINAch: A Diachronic Corpus of French Broadcast Speech Controlled for Speakers’ Age and Gender. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5805–5820, Palma de Mallorca, Spain. ELRA Language Resource Association.