We propose a recognition method for HMM using a simultaneous generative histogram. Proposed method uses the correlation between two features, which is expressed by a simultaneous generative histogram. Then output probabilities of integrated HMM are conditioned by the codeword of another feature. The proposed method is applied to isolated digit word recognition to confirm its validity.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yasuhisa HAYASHI, Akio OGIHARA, Kunio FUKUNAGA, "Speech Recognition of lsolated Digits Using Simultaneous Generative Histogram" in IEICE TRANSACTIONS on Fundamentals,
vol. E76-A, no. 12, pp. 2052-2054, December 1993, doi: .
Abstract: We propose a recognition method for HMM using a simultaneous generative histogram. Proposed method uses the correlation between two features, which is expressed by a simultaneous generative histogram. Then output probabilities of integrated HMM are conditioned by the codeword of another feature. The proposed method is applied to isolated digit word recognition to confirm its validity.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_12_2052/_p
Copy
@ARTICLE{e76-a_12_2052,
author={Yasuhisa HAYASHI, Akio OGIHARA, Kunio FUKUNAGA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Speech Recognition of lsolated Digits Using Simultaneous Generative Histogram},
year={1993},
volume={E76-A},
number={12},
pages={2052-2054},
abstract={We propose a recognition method for HMM using a simultaneous generative histogram. Proposed method uses the correlation between two features, which is expressed by a simultaneous generative histogram. Then output probabilities of integrated HMM are conditioned by the codeword of another feature. The proposed method is applied to isolated digit word recognition to confirm its validity.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - Speech Recognition of lsolated Digits Using Simultaneous Generative Histogram
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2052
EP - 2054
AU - Yasuhisa HAYASHI
AU - Akio OGIHARA
AU - Kunio FUKUNAGA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 1993
AB - We propose a recognition method for HMM using a simultaneous generative histogram. Proposed method uses the correlation between two features, which is expressed by a simultaneous generative histogram. Then output probabilities of integrated HMM are conditioned by the codeword of another feature. The proposed method is applied to isolated digit word recognition to confirm its validity.
ER -