@inproceedings{mohammadamini-etal-2024-robovox,
title = "{R}obo{V}ox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot",
author = "Mohammadamini, Mohammad and
Matrouf, Driss and
Rouvier, Michael and
Bonastre, Jean-Francois and
Serizel, Romain and
Gonos, Theophile",
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.1234",
pages = "14152--14156",
abstract = "In this paper, we introduce a new far-field speaker recognition benchmark called RoboVox. RoboVox is a French corpus recorded by a mobile robot. The files are recorded from different distances under severe acoustical conditions with the presence of several types of noise and reverberation. In addition to noise and reverberation, the robot{'}s internal noise acts as an extra additive noise. RoboVox can be used for both single-channel and multi-channel speaker recognition. In the evaluation protocols, we are considering both cases. The obtained results demonstrate a significant decline in performance in far-filed speaker recognition and urge the community to further research in this domain",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammadamini-etal-2024-robovox">
<titleInfo>
<title>RoboVox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Mohammadamini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Driss</namePart>
<namePart type="family">Matrouf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Rouvier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Francois</namePart>
<namePart type="family">Bonastre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romain</namePart>
<namePart type="family">Serizel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theophile</namePart>
<namePart type="family">Gonos</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>In this paper, we introduce a new far-field speaker recognition benchmark called RoboVox. RoboVox is a French corpus recorded by a mobile robot. The files are recorded from different distances under severe acoustical conditions with the presence of several types of noise and reverberation. In addition to noise and reverberation, the robot’s internal noise acts as an extra additive noise. RoboVox can be used for both single-channel and multi-channel speaker recognition. In the evaluation protocols, we are considering both cases. The obtained results demonstrate a significant decline in performance in far-filed speaker recognition and urge the community to further research in this domain</abstract>
<identifier type="citekey">mohammadamini-etal-2024-robovox</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1234</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14152</start>
<end>14156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoboVox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot
%A Mohammadamini, Mohammad
%A Matrouf, Driss
%A Rouvier, Michael
%A Bonastre, Jean-Francois
%A Serizel, Romain
%A Gonos, Theophile
%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 mohammadamini-etal-2024-robovox
%X In this paper, we introduce a new far-field speaker recognition benchmark called RoboVox. RoboVox is a French corpus recorded by a mobile robot. The files are recorded from different distances under severe acoustical conditions with the presence of several types of noise and reverberation. In addition to noise and reverberation, the robot’s internal noise acts as an extra additive noise. RoboVox can be used for both single-channel and multi-channel speaker recognition. In the evaluation protocols, we are considering both cases. The obtained results demonstrate a significant decline in performance in far-filed speaker recognition and urge the community to further research in this domain
%U https://aclanthology.org/2024.lrec-main.1234
%P 14152-14156
Markdown (Informal)
[RoboVox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot](https://aclanthology.org/2024.lrec-main.1234) (Mohammadamini et al., LREC-COLING 2024)
ACL