@inproceedings{moore-etal-2016-automated,
title = "Automated speech-unit delimitation in spoken learner {E}nglish",
author = "Moore, Russell and
Caines, Andrew and
Graham, Calbert and
Buttery, Paula",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1075/",
pages = "782--793",
abstract = "In order to apply computational linguistic analyses and pass information to downstream applications, transcriptions of speech obtained via automatic speech recognition (ASR) need to be divided into smaller meaningful units, in a task we refer to as `speech-unit (SU) delimitation'. We closely recreate the automatic delimitation system described by Lee and Glass (2012), `Sentence detection using multiple annotations', Proceedings of INTERSPEECH, which combines a prosodic model, language model and speech-unit length model in log-linear fashion. Since state-of-the-art natural language processing (NLP) tools have been developed to deal with written text and its characteristic sentence-like units, SU delimitation helps bridge the gap between ASR and NLP, by normalising spoken data into a more canonical format. Previous work has focused on native speaker recordings; we test the system of Lee and Glass (2012) on non-native speaker (or `learner') data, achieving performance above the state-of-the-art. We also consider alternative evaluation metrics which move away from the idea of a single `truth' in SU delimitation, and frame this work in the context of downstream NLP applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moore-etal-2016-automated">
<titleInfo>
<title>Automated speech-unit delimitation in spoken learner English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Russell</namePart>
<namePart type="family">Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Calbert</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In order to apply computational linguistic analyses and pass information to downstream applications, transcriptions of speech obtained via automatic speech recognition (ASR) need to be divided into smaller meaningful units, in a task we refer to as ‘speech-unit (SU) delimitation’. We closely recreate the automatic delimitation system described by Lee and Glass (2012), ‘Sentence detection using multiple annotations’, Proceedings of INTERSPEECH, which combines a prosodic model, language model and speech-unit length model in log-linear fashion. Since state-of-the-art natural language processing (NLP) tools have been developed to deal with written text and its characteristic sentence-like units, SU delimitation helps bridge the gap between ASR and NLP, by normalising spoken data into a more canonical format. Previous work has focused on native speaker recordings; we test the system of Lee and Glass (2012) on non-native speaker (or ‘learner’) data, achieving performance above the state-of-the-art. We also consider alternative evaluation metrics which move away from the idea of a single ‘truth’ in SU delimitation, and frame this work in the context of downstream NLP applications.</abstract>
<identifier type="citekey">moore-etal-2016-automated</identifier>
<location>
<url>https://aclanthology.org/C16-1075/</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>782</start>
<end>793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated speech-unit delimitation in spoken learner English
%A Moore, Russell
%A Caines, Andrew
%A Graham, Calbert
%A Buttery, Paula
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F moore-etal-2016-automated
%X In order to apply computational linguistic analyses and pass information to downstream applications, transcriptions of speech obtained via automatic speech recognition (ASR) need to be divided into smaller meaningful units, in a task we refer to as ‘speech-unit (SU) delimitation’. We closely recreate the automatic delimitation system described by Lee and Glass (2012), ‘Sentence detection using multiple annotations’, Proceedings of INTERSPEECH, which combines a prosodic model, language model and speech-unit length model in log-linear fashion. Since state-of-the-art natural language processing (NLP) tools have been developed to deal with written text and its characteristic sentence-like units, SU delimitation helps bridge the gap between ASR and NLP, by normalising spoken data into a more canonical format. Previous work has focused on native speaker recordings; we test the system of Lee and Glass (2012) on non-native speaker (or ‘learner’) data, achieving performance above the state-of-the-art. We also consider alternative evaluation metrics which move away from the idea of a single ‘truth’ in SU delimitation, and frame this work in the context of downstream NLP applications.
%U https://aclanthology.org/C16-1075/
%P 782-793
Markdown (Informal)
[Automated speech-unit delimitation in spoken learner English](https://aclanthology.org/C16-1075/) (Moore et al., COLING 2016)
ACL
- Russell Moore, Andrew Caines, Calbert Graham, and Paula Buttery. 2016. Automated speech-unit delimitation in spoken learner English. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 782–793, Osaka, Japan. The COLING 2016 Organizing Committee.