Open domain continuous Filipino speech recognition: Challenges and baseline experiments

In this paper, a new database suitable for HMM-based automatic Filipino speech recognition is described for the purpose of training a domain-independent, large-vocabulary continuous speech recognition system. Although it is known that high-performance speech recognition systems depend on a superior...

Full description

Saved in:
Bibliographic Details
Main Authors: Ang, Federico, Guevara, Rowena Cristina, Miyanaga, Yoshikazu, Cajote, Rhandley, Ilao, Joel P., Bayona, Michael Gringo Angelo, Laguna, Ann Franchesca B.
Format: text
Published: Animo Repository 2014
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/faculty_research/4039
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
id oai:animorepository.dlsu.edu.ph:faculty_research-4946
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:faculty_research-49462022-08-15T02:19:55Z Open domain continuous Filipino speech recognition: Challenges and baseline experiments Ang, Federico Guevara, Rowena Cristina Miyanaga, Yoshikazu Cajote, Rhandley Ilao, Joel P. Bayona, Michael Gringo Angelo Laguna, Ann Franchesca B. In this paper, a new database suitable for HMM-based automatic Filipino speech recognition is described for the purpose of training a domain-independent, large-vocabulary continuous speech recognition system. Although it is known that high-performance speech recognition systems depend on a superior speech database used in the training stage, due to the lack of such an appropriate database, previous reports on Filipino speech recognition had to contend with serious data sparsity issues. In this paper we alleviate such sparsity through appropriate data analysis that makes the evaluation results more reliable. The best system is identified through its low word-error rate to a cross-validation set containing almost three hours of unknown speech data. Language-dependent problems are discussed, and their impact on accuracy was analyzed. The approach is currently data driven, however it serves as a competent baseline model for succeeding future developments. Copyright © 2014 The Institute of Electronics, Information and Communication Engineers. 2014-01-01T08:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/4039 info:doi/10.1587/transinf.2013EDP7442 Faculty Research Work Animo Repository Automatic speech recognition Filipino language—Data processing Computer Sciences
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
topic Automatic speech recognition
Filipino language—Data processing
Computer Sciences
spellingShingle Automatic speech recognition
Filipino language—Data processing
Computer Sciences
Ang, Federico
Guevara, Rowena Cristina
Miyanaga, Yoshikazu
Cajote, Rhandley
Ilao, Joel P.
Bayona, Michael Gringo Angelo
Laguna, Ann Franchesca B.
Open domain continuous Filipino speech recognition: Challenges and baseline experiments
description In this paper, a new database suitable for HMM-based automatic Filipino speech recognition is described for the purpose of training a domain-independent, large-vocabulary continuous speech recognition system. Although it is known that high-performance speech recognition systems depend on a superior speech database used in the training stage, due to the lack of such an appropriate database, previous reports on Filipino speech recognition had to contend with serious data sparsity issues. In this paper we alleviate such sparsity through appropriate data analysis that makes the evaluation results more reliable. The best system is identified through its low word-error rate to a cross-validation set containing almost three hours of unknown speech data. Language-dependent problems are discussed, and their impact on accuracy was analyzed. The approach is currently data driven, however it serves as a competent baseline model for succeeding future developments. Copyright © 2014 The Institute of Electronics, Information and Communication Engineers.
format text
author Ang, Federico
Guevara, Rowena Cristina
Miyanaga, Yoshikazu
Cajote, Rhandley
Ilao, Joel P.
Bayona, Michael Gringo Angelo
Laguna, Ann Franchesca B.
author_facet Ang, Federico
Guevara, Rowena Cristina
Miyanaga, Yoshikazu
Cajote, Rhandley
Ilao, Joel P.
Bayona, Michael Gringo Angelo
Laguna, Ann Franchesca B.
author_sort Ang, Federico
title Open domain continuous Filipino speech recognition: Challenges and baseline experiments
title_short Open domain continuous Filipino speech recognition: Challenges and baseline experiments
title_full Open domain continuous Filipino speech recognition: Challenges and baseline experiments
title_fullStr Open domain continuous Filipino speech recognition: Challenges and baseline experiments
title_full_unstemmed Open domain continuous Filipino speech recognition: Challenges and baseline experiments
title_sort open domain continuous filipino speech recognition: challenges and baseline experiments
publisher Animo Repository
publishDate 2014
url https://animorepository.dlsu.edu.ph/faculty_research/4039
_version_ 1767196014900412416