@inproceedings{bentum-etal-2022-speech,
title = "A Speech Recognizer for {F}risian/{D}utch Council Meetings",
author = "Bentum, Martijn and
ten Bosch, Louis and
van den Heuvel, Henk and
Wills, Simone and
van der Niet, Domenique and
Dijkstra, Jelske and
Van de Velde, Hans",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.107",
pages = "1009--1015",
abstract = "We developed a bilingual Frisian/Dutch speech recognizer for council meetings in Frysl{\^a}n (the Netherlands). During these meetings both Frisian and Dutch are spoken, and code switching between both languages shows up frequently. The new speech recognizer is based on an existing speech recognizer for Frisian and Dutch named FAME!, which was trained and tested on historical radio broadcasts. Adapting a speech recognizer for the council meeting domain is challenging because of acoustic background noise, speaker overlap and the jargon typically used in council meetings. To train the new recognizer, we used the radio broadcast materials utilized for the development of the FAME! recognizer and added newly created manually transcribed audio recordings of council meetings from eleven Frisian municipalities, the Frisian provincial council and the Frisian water board. The council meeting recordings consist of 49 hours of speech, with 26 hours of Frisian speech and 23 hours of Dutch speech. Furthermore, from the same sources, we obtained texts in the domain of council meetings containing 11 million words; 1.1 million Frisian words and 9.9 million Dutch words. We describe the methods used to train the new recognizer, report the observed word error rates, and perform an error analysis on remaining errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bentum-etal-2022-speech">
<titleInfo>
<title>A Speech Recognizer for Frisian/Dutch Council Meetings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Bentum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">ten Bosch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Wills</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Domenique</namePart>
<namePart type="family">van der Niet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelske</namePart>
<namePart type="family">Dijkstra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hans</namePart>
<namePart type="family">Van de Velde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We developed a bilingual Frisian/Dutch speech recognizer for council meetings in Fryslân (the Netherlands). During these meetings both Frisian and Dutch are spoken, and code switching between both languages shows up frequently. The new speech recognizer is based on an existing speech recognizer for Frisian and Dutch named FAME!, which was trained and tested on historical radio broadcasts. Adapting a speech recognizer for the council meeting domain is challenging because of acoustic background noise, speaker overlap and the jargon typically used in council meetings. To train the new recognizer, we used the radio broadcast materials utilized for the development of the FAME! recognizer and added newly created manually transcribed audio recordings of council meetings from eleven Frisian municipalities, the Frisian provincial council and the Frisian water board. The council meeting recordings consist of 49 hours of speech, with 26 hours of Frisian speech and 23 hours of Dutch speech. Furthermore, from the same sources, we obtained texts in the domain of council meetings containing 11 million words; 1.1 million Frisian words and 9.9 million Dutch words. We describe the methods used to train the new recognizer, report the observed word error rates, and perform an error analysis on remaining errors.</abstract>
<identifier type="citekey">bentum-etal-2022-speech</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.107</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1009</start>
<end>1015</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Speech Recognizer for Frisian/Dutch Council Meetings
%A Bentum, Martijn
%A ten Bosch, Louis
%A van den Heuvel, Henk
%A Wills, Simone
%A van der Niet, Domenique
%A Dijkstra, Jelske
%A Van de Velde, Hans
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F bentum-etal-2022-speech
%X We developed a bilingual Frisian/Dutch speech recognizer for council meetings in Fryslân (the Netherlands). During these meetings both Frisian and Dutch are spoken, and code switching between both languages shows up frequently. The new speech recognizer is based on an existing speech recognizer for Frisian and Dutch named FAME!, which was trained and tested on historical radio broadcasts. Adapting a speech recognizer for the council meeting domain is challenging because of acoustic background noise, speaker overlap and the jargon typically used in council meetings. To train the new recognizer, we used the radio broadcast materials utilized for the development of the FAME! recognizer and added newly created manually transcribed audio recordings of council meetings from eleven Frisian municipalities, the Frisian provincial council and the Frisian water board. The council meeting recordings consist of 49 hours of speech, with 26 hours of Frisian speech and 23 hours of Dutch speech. Furthermore, from the same sources, we obtained texts in the domain of council meetings containing 11 million words; 1.1 million Frisian words and 9.9 million Dutch words. We describe the methods used to train the new recognizer, report the observed word error rates, and perform an error analysis on remaining errors.
%U https://aclanthology.org/2022.lrec-1.107
%P 1009-1015
Markdown (Informal)
[A Speech Recognizer for Frisian/Dutch Council Meetings](https://aclanthology.org/2022.lrec-1.107) (Bentum et al., LREC 2022)
ACL
- Martijn Bentum, Louis ten Bosch, Henk van den Heuvel, Simone Wills, Domenique van der Niet, Jelske Dijkstra, and Hans Van de Velde. 2022. A Speech Recognizer for Frisian/Dutch Council Meetings. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1009–1015, Marseille, France. European Language Resources Association.