@inproceedings{booth-etal-2020-evaluating,
title = "Evaluating and Improving Child-Directed Automatic Speech Recognition",
author = "Booth, Eric and
Carns, Jake and
Kennington, Casey and
Rafla, Nader",
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-1.778",
pages = "6340--6345",
abstract = "Speech recognition has seen dramatic improvements in the last decade, though those improvements have focused primarily on adult speech. In this paper, we assess child-directed speech recognition and leverage a transfer learning approach to improve child-directed speech recognition by training the recent DeepSpeech2 model on adult data, then apply additional tuning to varied amounts of child speech data. We evaluate our model using the CMU Kids dataset as well as our own recordings of child-directed prompts. The results from our experiment show that even a small amount of child audio data improves significantly over a baseline of adult-only or child-only trained models. We report a final general Word-Error-Rate of 29{\%} over a baseline of 62{\%} that uses the adult-trained model. Our analyses show that our model adapts quickly using a small amount of data and that the general child model works better than school grade-specific models. We make available our trained model and our data collection tool.",
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="booth-etal-2020-evaluating">
<titleInfo>
<title>Evaluating and Improving Child-Directed Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Booth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Carns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nader</namePart>
<namePart type="family">Rafla</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>Speech recognition has seen dramatic improvements in the last decade, though those improvements have focused primarily on adult speech. In this paper, we assess child-directed speech recognition and leverage a transfer learning approach to improve child-directed speech recognition by training the recent DeepSpeech2 model on adult data, then apply additional tuning to varied amounts of child speech data. We evaluate our model using the CMU Kids dataset as well as our own recordings of child-directed prompts. The results from our experiment show that even a small amount of child audio data improves significantly over a baseline of adult-only or child-only trained models. We report a final general Word-Error-Rate of 29% over a baseline of 62% that uses the adult-trained model. Our analyses show that our model adapts quickly using a small amount of data and that the general child model works better than school grade-specific models. We make available our trained model and our data collection tool.</abstract>
<identifier type="citekey">booth-etal-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.778</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6340</start>
<end>6345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating and Improving Child-Directed Automatic Speech Recognition
%A Booth, Eric
%A Carns, Jake
%A Kennington, Casey
%A Rafla, Nader
%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 booth-etal-2020-evaluating
%X Speech recognition has seen dramatic improvements in the last decade, though those improvements have focused primarily on adult speech. In this paper, we assess child-directed speech recognition and leverage a transfer learning approach to improve child-directed speech recognition by training the recent DeepSpeech2 model on adult data, then apply additional tuning to varied amounts of child speech data. We evaluate our model using the CMU Kids dataset as well as our own recordings of child-directed prompts. The results from our experiment show that even a small amount of child audio data improves significantly over a baseline of adult-only or child-only trained models. We report a final general Word-Error-Rate of 29% over a baseline of 62% that uses the adult-trained model. Our analyses show that our model adapts quickly using a small amount of data and that the general child model works better than school grade-specific models. We make available our trained model and our data collection tool.
%U https://aclanthology.org/2020.lrec-1.778
%P 6340-6345
Markdown (Informal)
[Evaluating and Improving Child-Directed Automatic Speech Recognition](https://aclanthology.org/2020.lrec-1.778) (Booth et al., LREC 2020)
ACL