@inproceedings{zahrer-etal-2020-towards,
title = "Towards Building an Automatic Transcription System for Language Documentation: Experiences from {M}uyu",
author = "Zahrer, Alexander and
Zgank, Andrej and
Schuppler, Barbara",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.353",
pages = "2893--2900",
abstract = "Since at least half of the world{'}s 6000 plus languages will vanish during the 21st century, language documentation has become a rapidly growing field in linguistics. A fundamental challenge for language documentation is the {''}transcription bottleneck{''}. Speech technology may deliver the decisive breakthrough for overcoming the transcription bottleneck. This paper presents first experiments from the development of ASR4LD, a new automatic speech recognition (ASR) based tool for language documentation (LD). The experiments are based on recordings from an ongoing documentation project for the endangered Muyu language in New Guinea. We compare phoneme recognition experiments with American English, Austrian German and Slovenian as source language and Muyu as target language. The Slovenian acoustic models achieve the by far best performance (43.71{\%} PER) in comparison to 57.14{\%} PER with American English, and 89.49{\%} PER with Austrian German. Whereas part of the errors can be explained by phonetic variation, the recording mismatch poses a major problem. On the long term, ASR4LD will not only be an integral part of the ongoing documentation project of Muyu, but will be further developed in order to facilitate also the language documentation process of other language groups.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zahrer-etal-2020-towards">
<titleInfo>
<title>Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Zahrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrej</namePart>
<namePart type="family">Zgank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Schuppler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Since at least half of the world’s 6000 plus languages will vanish during the 21st century, language documentation has become a rapidly growing field in linguistics. A fundamental challenge for language documentation is the ”transcription bottleneck”. Speech technology may deliver the decisive breakthrough for overcoming the transcription bottleneck. This paper presents first experiments from the development of ASR4LD, a new automatic speech recognition (ASR) based tool for language documentation (LD). The experiments are based on recordings from an ongoing documentation project for the endangered Muyu language in New Guinea. We compare phoneme recognition experiments with American English, Austrian German and Slovenian as source language and Muyu as target language. The Slovenian acoustic models achieve the by far best performance (43.71% PER) in comparison to 57.14% PER with American English, and 89.49% PER with Austrian German. Whereas part of the errors can be explained by phonetic variation, the recording mismatch poses a major problem. On the long term, ASR4LD will not only be an integral part of the ongoing documentation project of Muyu, but will be further developed in order to facilitate also the language documentation process of other language groups.</abstract>
<identifier type="citekey">zahrer-etal-2020-towards</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.353</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2893</start>
<end>2900</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu
%A Zahrer, Alexander
%A Zgank, Andrej
%A Schuppler, Barbara
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F zahrer-etal-2020-towards
%X Since at least half of the world’s 6000 plus languages will vanish during the 21st century, language documentation has become a rapidly growing field in linguistics. A fundamental challenge for language documentation is the ”transcription bottleneck”. Speech technology may deliver the decisive breakthrough for overcoming the transcription bottleneck. This paper presents first experiments from the development of ASR4LD, a new automatic speech recognition (ASR) based tool for language documentation (LD). The experiments are based on recordings from an ongoing documentation project for the endangered Muyu language in New Guinea. We compare phoneme recognition experiments with American English, Austrian German and Slovenian as source language and Muyu as target language. The Slovenian acoustic models achieve the by far best performance (43.71% PER) in comparison to 57.14% PER with American English, and 89.49% PER with Austrian German. Whereas part of the errors can be explained by phonetic variation, the recording mismatch poses a major problem. On the long term, ASR4LD will not only be an integral part of the ongoing documentation project of Muyu, but will be further developed in order to facilitate also the language documentation process of other language groups.
%U https://aclanthology.org/2020.lrec-1.353
%P 2893-2900
Markdown (Informal)
[Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu](https://aclanthology.org/2020.lrec-1.353) (Zahrer et al., LREC 2020)
ACL