@inproceedings{tahon-etal-2024-allies-speech,
title = "{ALLIES}: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection",
author = "Tahon, Marie and
Larcher, Anthony and
Lebourdais, Martin and
Bougares, Fethi and
Silnova, Anna and
Gimeno, Pablo",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.67",
pages = "751--758",
abstract = "This paper presents ALLIES, a meta corpus which gathers and extends existing French corpora collected from radio and TV shows. The corpus contains 1048 audio files for about 500 hours of speech. Agglomeration of data is always a difficult issue, as the guidelines used to collect, annotate and transcribe speech are generally different from one corpus to another. ALLIES intends to homogenize and correct speaker labels among the different files by integrated human feedback within a speaker verification system. The main contribution of this article is the design of a protocol in order to evaluate properly speech segmentation (including music and overlap detection), speaker diarization, speech transcription and speaker change detection. As part of it, a test partition has been carefully manually 1) segmented and annotated according to speech, music, noise, speaker labels with specific guidelines for overlap speech, 2) orthographically transcribed. This article also provides as a second contribution baseline results for several speech processing tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahon-etal-2024-allies-speech">
<titleInfo>
<title>ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Tahon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Larcher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Lebourdais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Silnova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gimeno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents ALLIES, a meta corpus which gathers and extends existing French corpora collected from radio and TV shows. The corpus contains 1048 audio files for about 500 hours of speech. Agglomeration of data is always a difficult issue, as the guidelines used to collect, annotate and transcribe speech are generally different from one corpus to another. ALLIES intends to homogenize and correct speaker labels among the different files by integrated human feedback within a speaker verification system. The main contribution of this article is the design of a protocol in order to evaluate properly speech segmentation (including music and overlap detection), speaker diarization, speech transcription and speaker change detection. As part of it, a test partition has been carefully manually 1) segmented and annotated according to speech, music, noise, speaker labels with specific guidelines for overlap speech, 2) orthographically transcribed. This article also provides as a second contribution baseline results for several speech processing tasks.</abstract>
<identifier type="citekey">tahon-etal-2024-allies-speech</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.67</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>751</start>
<end>758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection
%A Tahon, Marie
%A Larcher, Anthony
%A Lebourdais, Martin
%A Bougares, Fethi
%A Silnova, Anna
%A Gimeno, Pablo
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F tahon-etal-2024-allies-speech
%X This paper presents ALLIES, a meta corpus which gathers and extends existing French corpora collected from radio and TV shows. The corpus contains 1048 audio files for about 500 hours of speech. Agglomeration of data is always a difficult issue, as the guidelines used to collect, annotate and transcribe speech are generally different from one corpus to another. ALLIES intends to homogenize and correct speaker labels among the different files by integrated human feedback within a speaker verification system. The main contribution of this article is the design of a protocol in order to evaluate properly speech segmentation (including music and overlap detection), speaker diarization, speech transcription and speaker change detection. As part of it, a test partition has been carefully manually 1) segmented and annotated according to speech, music, noise, speaker labels with specific guidelines for overlap speech, 2) orthographically transcribed. This article also provides as a second contribution baseline results for several speech processing tasks.
%U https://aclanthology.org/2024.lrec-main.67
%P 751-758
Markdown (Informal)
[ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection](https://aclanthology.org/2024.lrec-main.67) (Tahon et al., LREC-COLING 2024)
ACL
- Marie Tahon, Anthony Larcher, Martin Lebourdais, Fethi Bougares, Anna Silnova, and Pablo Gimeno. 2024. ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 751–758, Torino, Italia. ELRA and ICCL.