Response Time Reduction of Speech Recognizers Using Single Gaussians

Sangbae JEONG; Hoirin KIM; Minsoo HAHN

doi:10.1093/ietisy/e90-d.5.868

Response Time Reduction of Speech Recognizers Using Single Gaussians

Sangbae JEONG, Hoirin KIM, Minsoo HAHN

Full Text Views

0

Share
Cite this

Summary :

In this paper, we propose a useful algorithm that can be applied to reduce the response time of speech recognizers based on HMM's. In our algorithm, to reduce the response time, promising HMM states are selected by single Gaussians. In speech recognition, HMM state likelihoods are evaluated by the corresponding single Gaussians first, and then likelihoods by original full Gaussians are computed and replaced only for the HMM states having relatively large likelihoods. By doing so, we can reduce the pattern-matching time for speech recognition significantly without any noticeable loss of the recognition rate. In addition, we cluster the single Gaussians into groups by measuring the distance between Gaussians. Therefore, we can reduce the extra memory much more. In our 10,000 word Korean POI (point-of-interest) recognition task, our proposed algorithm shows 35.57% reduction of the response time in comparison with that of the baseline system at the cost of 10% degradation of the WER.

Publication: IEICE TRANSACTIONS on Information Vol.E90-D No.5 pp.868-871

Publication Date: 2007/05/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e90-d.5.868

Type of Manuscript: LETTER

Category: Speech and Hearing

Cite this

Copy

Sangbae JEONG, Hoirin KIM, Minsoo HAHN, "Response Time Reduction of Speech Recognizers Using Single Gaussians" in IEICE TRANSACTIONS on Information, vol. E90-D, no. 5, pp. 868-871, May 2007, doi: 10.1093/ietisy/e90-d.5.868.
Abstract: In this paper, we propose a useful algorithm that can be applied to reduce the response time of speech recognizers based on HMM's. In our algorithm, to reduce the response time, promising HMM states are selected by single Gaussians. In speech recognition, HMM state likelihoods are evaluated by the corresponding single Gaussians first, and then likelihoods by original full Gaussians are computed and replaced only for the HMM states having relatively large likelihoods. By doing so, we can reduce the pattern-matching time for speech recognition significantly without any noticeable loss of the recognition rate. In addition, we cluster the single Gaussians into groups by measuring the distance between Gaussians. Therefore, we can reduce the extra memory much more. In our 10,000 word Korean POI (point-of-interest) recognition task, our proposed algorithm shows 35.57% reduction of the response time in comparison with that of the baseline system at the cost of 10% degradation of the WER.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.5.868/_p

Copy

@ARTICLE{e90-d_5_868,
author={Sangbae JEONG, Hoirin KIM, Minsoo HAHN, },
journal={IEICE TRANSACTIONS on Information},
title={Response Time Reduction of Speech Recognizers Using Single Gaussians},
year={2007},
volume={E90-D},
number={5},
pages={868-871},
abstract={In this paper, we propose a useful algorithm that can be applied to reduce the response time of speech recognizers based on HMM's. In our algorithm, to reduce the response time, promising HMM states are selected by single Gaussians. In speech recognition, HMM state likelihoods are evaluated by the corresponding single Gaussians first, and then likelihoods by original full Gaussians are computed and replaced only for the HMM states having relatively large likelihoods. By doing so, we can reduce the pattern-matching time for speech recognition significantly without any noticeable loss of the recognition rate. In addition, we cluster the single Gaussians into groups by measuring the distance between Gaussians. Therefore, we can reduce the extra memory much more. In our 10,000 word Korean POI (point-of-interest) recognition task, our proposed algorithm shows 35.57% reduction of the response time in comparison with that of the baseline system at the cost of 10% degradation of the WER.},
keywords={},
doi={10.1093/ietisy/e90-d.5.868},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Response Time Reduction of Speech Recognizers Using Single Gaussians
T2 - IEICE TRANSACTIONS on Information
SP - 868
EP - 871
AU - Sangbae JEONG
AU - Hoirin KIM
AU - Minsoo HAHN
PY - 2007
DO - 10.1093/ietisy/e90-d.5.868
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2007
AB - In this paper, we propose a useful algorithm that can be applied to reduce the response time of speech recognizers based on HMM's. In our algorithm, to reduce the response time, promising HMM states are selected by single Gaussians. In speech recognition, HMM state likelihoods are evaluated by the corresponding single Gaussians first, and then likelihoods by original full Gaussians are computed and replaced only for the HMM states having relatively large likelihoods. By doing so, we can reduce the pattern-matching time for speech recognition significantly without any noticeable loss of the recognition rate. In addition, we cluster the single Gaussians into groups by measuring the distance between Gaussians. Therefore, we can reduce the extra memory much more. In our 10,000 word Korean POI (point-of-interest) recognition task, our proposed algorithm shows 35.57% reduction of the response time in comparison with that of the baseline system at the cost of 10% degradation of the WER.
ER -