@inproceedings{adhikary-etal-2019-investigating,
title = "Investigating Speech Recognition for Improving Predictive {AAC}",
author = "Adhikary, Jiban and
Watling, Robbie and
Fletcher, Crystal and
Stanage, Alex and
Vertanen, Keith",
editor = "Christensen, Heidi and
Hollingshead, Kristy and
Prud{'}hommeaux, Emily and
Rudzicz, Frank and
Vertanen, Keith",
booktitle = "Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1706",
doi = "10.18653/v1/W19-1706",
pages = "37--43",
abstract = "Making good letter or word predictions can help accelerate the communication of users of high-tech AAC devices. This is particularly important for real-time person-to-person conversations. We investigate whether per forming speech recognition on the speaking-side of a conversation can improve language model based predictions. We compare the accuracy of three plausible microphone deployment options and the accuracy of two commercial speech recognition engines (Google and IBM Watson). We found that despite recognition word error rates of 7-16{\%}, our ensemble of N-gram and recurrent neural network language models made predictions nearly as good as when they used the reference transcripts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adhikary-etal-2019-investigating">
<titleInfo>
<title>Investigating Speech Recognition for Improving Predictive AAC</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiban</namePart>
<namePart type="family">Adhikary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robbie</namePart>
<namePart type="family">Watling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crystal</namePart>
<namePart type="family">Fletcher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Stanage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Vertanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heidi</namePart>
<namePart type="family">Christensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristy</namePart>
<namePart type="family">Hollingshead</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Prud’hommeaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Rudzicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Vertanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Making good letter or word predictions can help accelerate the communication of users of high-tech AAC devices. This is particularly important for real-time person-to-person conversations. We investigate whether per forming speech recognition on the speaking-side of a conversation can improve language model based predictions. We compare the accuracy of three plausible microphone deployment options and the accuracy of two commercial speech recognition engines (Google and IBM Watson). We found that despite recognition word error rates of 7-16%, our ensemble of N-gram and recurrent neural network language models made predictions nearly as good as when they used the reference transcripts.</abstract>
<identifier type="citekey">adhikary-etal-2019-investigating</identifier>
<identifier type="doi">10.18653/v1/W19-1706</identifier>
<location>
<url>https://aclanthology.org/W19-1706</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>37</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Speech Recognition for Improving Predictive AAC
%A Adhikary, Jiban
%A Watling, Robbie
%A Fletcher, Crystal
%A Stanage, Alex
%A Vertanen, Keith
%Y Christensen, Heidi
%Y Hollingshead, Kristy
%Y Prud’hommeaux, Emily
%Y Rudzicz, Frank
%Y Vertanen, Keith
%S Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F adhikary-etal-2019-investigating
%X Making good letter or word predictions can help accelerate the communication of users of high-tech AAC devices. This is particularly important for real-time person-to-person conversations. We investigate whether per forming speech recognition on the speaking-side of a conversation can improve language model based predictions. We compare the accuracy of three plausible microphone deployment options and the accuracy of two commercial speech recognition engines (Google and IBM Watson). We found that despite recognition word error rates of 7-16%, our ensemble of N-gram and recurrent neural network language models made predictions nearly as good as when they used the reference transcripts.
%R 10.18653/v1/W19-1706
%U https://aclanthology.org/W19-1706
%U https://doi.org/10.18653/v1/W19-1706
%P 37-43
Markdown (Informal)
[Investigating Speech Recognition for Improving Predictive AAC](https://aclanthology.org/W19-1706) (Adhikary et al., SLPAT 2019)
ACL
- Jiban Adhikary, Robbie Watling, Crystal Fletcher, Alex Stanage, and Keith Vertanen. 2019. Investigating Speech Recognition for Improving Predictive AAC. In Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies, pages 37–43, Minneapolis, Minnesota. Association for Computational Linguistics.