@inproceedings{nimaan-etal-2006-towards,
title = "Towards automatic transcription of {S}omali language",
author = "Nimaan, Abdillahi and
Nocera, Pascal and
Bonastre, Jean-Fran{\c{c}}ois",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/801_pdf.pdf",
abstract = "Most African countries follow an oral tradition system to transmit their cultural, scientific and historic heritage through generations. This ancestral knowledge accumulated during centuries is today threatened of disappearing. This paper presents the first steps in the building of an automatic speech to text transcription for African oral patrimony, particularly the Djibouti cultural heritage. This work is dedicated to process Somali language, which represents half of the targeted Djiboutian audio archives. The main problem is the lack of annotated audio and textual resources for this language. We describe the principal characteristics of audio (10 hours) and textual (3M words) training corpora collected. Using the large vocabulary speech recognizer engine, Speeral, developed at the Laboratoire Informatique dAvignon (LIA) (computer science laboratory of Avignon), we obtain about 20.9{\%} word error rate (WER). This is an encouraging result, considering the small size of our corpora. This first recognizer of Somali language will serve as a reference and will be used to transcribe some Djibouti cultural archives. We will also discuss future ways of research like sub-words indexing of audio archives, related to the specificities of the Somali language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nimaan-etal-2006-towards">
<titleInfo>
<title>Towards automatic transcription of Somali language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdillahi</namePart>
<namePart type="family">Nimaan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascal</namePart>
<namePart type="family">Nocera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-François</namePart>
<namePart type="family">Bonastre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most African countries follow an oral tradition system to transmit their cultural, scientific and historic heritage through generations. This ancestral knowledge accumulated during centuries is today threatened of disappearing. This paper presents the first steps in the building of an automatic speech to text transcription for African oral patrimony, particularly the Djibouti cultural heritage. This work is dedicated to process Somali language, which represents half of the targeted Djiboutian audio archives. The main problem is the lack of annotated audio and textual resources for this language. We describe the principal characteristics of audio (10 hours) and textual (3M words) training corpora collected. Using the large vocabulary speech recognizer engine, Speeral, developed at the Laboratoire Informatique dAvignon (LIA) (computer science laboratory of Avignon), we obtain about 20.9% word error rate (WER). This is an encouraging result, considering the small size of our corpora. This first recognizer of Somali language will serve as a reference and will be used to transcribe some Djibouti cultural archives. We will also discuss future ways of research like sub-words indexing of audio archives, related to the specificities of the Somali language.</abstract>
<identifier type="citekey">nimaan-etal-2006-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/801_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards automatic transcription of Somali language
%A Nimaan, Abdillahi
%A Nocera, Pascal
%A Bonastre, Jean-François
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F nimaan-etal-2006-towards
%X Most African countries follow an oral tradition system to transmit their cultural, scientific and historic heritage through generations. This ancestral knowledge accumulated during centuries is today threatened of disappearing. This paper presents the first steps in the building of an automatic speech to text transcription for African oral patrimony, particularly the Djibouti cultural heritage. This work is dedicated to process Somali language, which represents half of the targeted Djiboutian audio archives. The main problem is the lack of annotated audio and textual resources for this language. We describe the principal characteristics of audio (10 hours) and textual (3M words) training corpora collected. Using the large vocabulary speech recognizer engine, Speeral, developed at the Laboratoire Informatique dAvignon (LIA) (computer science laboratory of Avignon), we obtain about 20.9% word error rate (WER). This is an encouraging result, considering the small size of our corpora. This first recognizer of Somali language will serve as a reference and will be used to transcribe some Djibouti cultural archives. We will also discuss future ways of research like sub-words indexing of audio archives, related to the specificities of the Somali language.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/801_pdf.pdf
Markdown (Informal)
[Towards automatic transcription of Somali language](http://www.lrec-conf.org/proceedings/lrec2006/pdf/801_pdf.pdf) (Nimaan et al., LREC 2006)
ACL
- Abdillahi Nimaan, Pascal Nocera, and Jean-François Bonastre. 2006. Towards automatic transcription of Somali language. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).