Post-error Correction in Automatic Speech Recognition Using Discourse Information
Overcoming speech recognition errors in the field of human�computer interaction is important in ensuring a consistent user experience. This paper proposes a semantic-oriented post-processing approach for the correction of errors in speech recognition. The novelty of the model proposed here is tha...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Stefan cel Mare University of Suceava
2014-05-01
|
Series: | Advances in Electrical and Computer Engineering |
Subjects: | |
Online Access: | http://dx.doi.org/10.4316/AECE.2014.02009 |
id |
doaj-b5c22469c99c49eebd95cf0e73c9e701 |
---|---|
record_format |
Article |
spelling |
doaj-b5c22469c99c49eebd95cf0e73c9e7012020-11-25T00:01:29ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002014-05-01142535610.4316/AECE.2014.02009Post-error Correction in Automatic Speech Recognition Using Discourse InformationKANG, S.KIM, J.-H.SEO, J. Overcoming speech recognition errors in the field of human�computer interaction is important in ensuring a consistent user experience. This paper proposes a semantic-oriented post-processing approach for the correction of errors in speech recognition. The novelty of the model proposed here is that it re-ranks the n-best hypothesis of speech recognition based on the user's intention, which is analyzed from previous discourse information, while conventional automatic speech recognition systems focus only on acoustic and language model scores for the current sentence. The proposed model successfully reduces the word error rate and semantic error rate by 3.65% and 8.61%, respectively.http://dx.doi.org/10.4316/AECE.2014.02009post correctionspeech recognitionre-ranking modelanalysis of user intentionspoken language understandingspoken dialog system |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
KANG, S. KIM, J.-H. SEO, J. |
spellingShingle |
KANG, S. KIM, J.-H. SEO, J. Post-error Correction in Automatic Speech Recognition Using Discourse Information Advances in Electrical and Computer Engineering post correction speech recognition re-ranking model analysis of user intention spoken language understanding spoken dialog system |
author_facet |
KANG, S. KIM, J.-H. SEO, J. |
author_sort |
KANG, S. |
title |
Post-error Correction in Automatic Speech Recognition Using Discourse Information |
title_short |
Post-error Correction in Automatic Speech Recognition Using Discourse Information |
title_full |
Post-error Correction in Automatic Speech Recognition Using Discourse Information |
title_fullStr |
Post-error Correction in Automatic Speech Recognition Using Discourse Information |
title_full_unstemmed |
Post-error Correction in Automatic Speech Recognition Using Discourse Information |
title_sort |
post-error correction in automatic speech recognition using discourse information |
publisher |
Stefan cel Mare University of Suceava |
series |
Advances in Electrical and Computer Engineering |
issn |
1582-7445 1844-7600 |
publishDate |
2014-05-01 |
description |
Overcoming speech recognition errors in the field of human�computer interaction is important in ensuring
a consistent user experience. This paper proposes a semantic-oriented post-processing approach for the
correction of errors in speech recognition. The novelty of the model proposed here is that it re-ranks
the n-best hypothesis of speech recognition based on the user's intention, which is analyzed from previous
discourse information, while conventional automatic speech recognition systems focus only on acoustic and
language model scores for the current sentence. The proposed model successfully reduces the word error rate
and semantic error rate by 3.65% and 8.61%, respectively. |
topic |
post correction speech recognition re-ranking model analysis of user intention spoken language understanding spoken dialog system |
url |
http://dx.doi.org/10.4316/AECE.2014.02009 |
work_keys_str_mv |
AT kangs posterrorcorrectioninautomaticspeechrecognitionusingdiscourseinformation AT kimjh posterrorcorrectioninautomaticspeechrecognitionusingdiscourseinformation AT seoj posterrorcorrectioninautomaticspeechrecognitionusingdiscourseinformation |
_version_ |
1725441851960328192 |