@inproceedings{chen-etal-2022-automatically,
title = "Automatically Detecting Reduced-formed {E}nglish Pronunciations by Using Deep Learning",
author = "Chen, Lei and
Jiang, Chenglin and
Gu, Yiwei and
Liu, Yang and
Yuan, Jiahong",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bea-1.4",
doi = "10.18653/v1/2022.bea-1.4",
pages = "22--26",
abstract = "Reduced form pronunciations are widely used by native English speakers, especially in casual conversations. Second language (L2) learners have difficulty in processing reduced form pronunciations in listening comprehension and face challenges in production too. Meanwhile, training applications dedicated to reduced forms are still few. To solve this issue, we report on our first effort of using deep learning to evaluate L2 learners{'} reduced form pronunciations. Compared with a baseline solution that uses an ASR to determine regular or reduced-formed pronunciations, a classifier that learns representative features via a convolution neural network (CNN) on low-level acoustic features, yields higher detection performance. F-1 metric has been increased from 0.690 to 0.757 on the reduction task. Furthermore, adding word entities to compute attention weights to better adjust the features learned by the CNN model helps increasing F-1 to 0.763.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-automatically">
<titleInfo>
<title>Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenglin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwei</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahong</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reduced form pronunciations are widely used by native English speakers, especially in casual conversations. Second language (L2) learners have difficulty in processing reduced form pronunciations in listening comprehension and face challenges in production too. Meanwhile, training applications dedicated to reduced forms are still few. To solve this issue, we report on our first effort of using deep learning to evaluate L2 learners’ reduced form pronunciations. Compared with a baseline solution that uses an ASR to determine regular or reduced-formed pronunciations, a classifier that learns representative features via a convolution neural network (CNN) on low-level acoustic features, yields higher detection performance. F-1 metric has been increased from 0.690 to 0.757 on the reduction task. Furthermore, adding word entities to compute attention weights to better adjust the features learned by the CNN model helps increasing F-1 to 0.763.</abstract>
<identifier type="citekey">chen-etal-2022-automatically</identifier>
<identifier type="doi">10.18653/v1/2022.bea-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.bea-1.4</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>22</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning
%A Chen, Lei
%A Jiang, Chenglin
%A Gu, Yiwei
%A Liu, Yang
%A Yuan, Jiahong
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F chen-etal-2022-automatically
%X Reduced form pronunciations are widely used by native English speakers, especially in casual conversations. Second language (L2) learners have difficulty in processing reduced form pronunciations in listening comprehension and face challenges in production too. Meanwhile, training applications dedicated to reduced forms are still few. To solve this issue, we report on our first effort of using deep learning to evaluate L2 learners’ reduced form pronunciations. Compared with a baseline solution that uses an ASR to determine regular or reduced-formed pronunciations, a classifier that learns representative features via a convolution neural network (CNN) on low-level acoustic features, yields higher detection performance. F-1 metric has been increased from 0.690 to 0.757 on the reduction task. Furthermore, adding word entities to compute attention weights to better adjust the features learned by the CNN model helps increasing F-1 to 0.763.
%R 10.18653/v1/2022.bea-1.4
%U https://aclanthology.org/2022.bea-1.4
%U https://doi.org/10.18653/v1/2022.bea-1.4
%P 22-26
Markdown (Informal)
[Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning](https://aclanthology.org/2022.bea-1.4) (Chen et al., BEA 2022)
ACL