@article{bird-2020-sparse,
title = "Sparse Transcription",
author = "Bird, Steven",
journal = "Computational Linguistics",
volume = "46",
number = "4",
month = dec,
year = "2020",
url = "https://aclanthology.org/2020.cl-4.1",
doi = "10.1162/coli_a_00387",
pages = "713--744",
abstract = "The transcription bottleneck is often cited as a major obstacle for efforts to document the world{'}s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech recognition and machine translation, and recruit linguists to provide narrow phonetic transcriptions and sentence-aligned translations. However, I believe that these approaches are not a good fit with the available data and skills, or with long-established practices that are essentially word-based. In seeking a more effective approach, I consider a century of transcription practice and a wide range of computational approaches, before proposing a computational model based on spoken term detection that I call {``}sparse transcription.{''} This represents a shift away from current assumptions that we transcribe phones, transcribe fully, and transcribe first. Instead, sparse transcription combines the older practice of word-level transcription with interpretive, iterative, and interactive processes that are amenable to wider participation and that open the way to new methods for processing oral languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bird-2020-sparse">
<titleInfo>
<title>Sparse Transcription</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bird</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>The transcription bottleneck is often cited as a major obstacle for efforts to document the world’s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech recognition and machine translation, and recruit linguists to provide narrow phonetic transcriptions and sentence-aligned translations. However, I believe that these approaches are not a good fit with the available data and skills, or with long-established practices that are essentially word-based. In seeking a more effective approach, I consider a century of transcription practice and a wide range of computational approaches, before proposing a computational model based on spoken term detection that I call “sparse transcription.” This represents a shift away from current assumptions that we transcribe phones, transcribe fully, and transcribe first. Instead, sparse transcription combines the older practice of word-level transcription with interpretive, iterative, and interactive processes that are amenable to wider participation and that open the way to new methods for processing oral languages.</abstract>
<identifier type="citekey">bird-2020-sparse</identifier>
<identifier type="doi">10.1162/coli_a_00387</identifier>
<location>
<url>https://aclanthology.org/2020.cl-4.1</url>
</location>
<part>
<date>2020-12</date>
<detail type="volume"><number>46</number></detail>
<detail type="issue"><number>4</number></detail>
<extent unit="page">
<start>713</start>
<end>744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Sparse Transcription
%A Bird, Steven
%J Computational Linguistics
%D 2020
%8 December
%V 46
%N 4
%F bird-2020-sparse
%X The transcription bottleneck is often cited as a major obstacle for efforts to document the world’s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech recognition and machine translation, and recruit linguists to provide narrow phonetic transcriptions and sentence-aligned translations. However, I believe that these approaches are not a good fit with the available data and skills, or with long-established practices that are essentially word-based. In seeking a more effective approach, I consider a century of transcription practice and a wide range of computational approaches, before proposing a computational model based on spoken term detection that I call “sparse transcription.” This represents a shift away from current assumptions that we transcribe phones, transcribe fully, and transcribe first. Instead, sparse transcription combines the older practice of word-level transcription with interpretive, iterative, and interactive processes that are amenable to wider participation and that open the way to new methods for processing oral languages.
%R 10.1162/coli_a_00387
%U https://aclanthology.org/2020.cl-4.1
%U https://doi.org/10.1162/coli_a_00387
%P 713-744
Markdown (Informal)
[Sparse Transcription](https://aclanthology.org/2020.cl-4.1) (Bird, CL 2020)
ACL