A study of speech recognition system based on the Hidden Markov Model with Gaussian-Mixture

被引：0

作者：

Ben Hazem, Zied ^{[1
]}

Zouhir, Youssef ^{[1
]}

Ouni, Kais ^{[1
]}

机构：

[1] Univ Carthage, Higher Sch Technol & Comp Sci ESTI, Res Unit Signals & Mechatron Syst, SMS, Carthage, Tunisia

来源：

2014 INTERNATIONAL CONFERENCE ON ELECTRICAL SCIENCES AND TECHNOLOGIES IN MAGHREB (CISTEM) | 2014年

关键词：

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In this paper, we present a study of isolated word speech recognition system. The adopted system is based on the Hidden Markov Model with Gaussian Mixture (HMM-GM). We studied the recognition rate by varying the states number (3, 4, 5, 6 and 7 states) and the number of Gaussians per state (2, 4, 8, 12, 14 and 16 Gaussians) of Hidden Markov Model. We evaluated these recognition rates using two parameterization techniques Mel Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP). We have introduced the dynamic coefficients and the energy of the signal in order to achieve an improvement in the recognition rate.

引用

页数：5

共 50 条

[41] STATE CLUSTERING IN HIDDEN MARKOV MODEL-BASED CONTINUOUS SPEECH RECOGNITION
YOUNG, SJ
WOODLAND, PC
[J]. COMPUTER SPEECH AND LANGUAGE, 1994, 8 (04): : 369 - 383
[42] A Gaussian-Mixture Model Algorithm and Platform for HDR QA
Thorne, N.
He, R.
Yang, C.
[J]. MEDICAL PHYSICS, 2017, 44 (06) : 3145 - 3145
[43] On a study of decreasing the processing time in the speech recognition system using the HMM(hidden Markov model) algorithm
Min, S
Bae, M
[J]. 2001 MILCOM, VOLS 1 AND 2, PROCEEDINGS: COMMUNICATIONS FOR NETWORK-CENTRIC OPERATIONS: CREATING THE INFORMATION FORCE, 2001, : 1224 - 1228
[44] An optic-fiber fence intrusion recognition system using mixture Gaussian hidden Markov models
Ma, Zhixian
Liang, Yao
Zhu, Jie
[J]. IEICE ELECTRONICS EXPRESS, 2017, 14 (05):
[45] A Gaussian mixture-hidden Markov model of human visual behavior
Liu H.
Zheng X.
Wang Y.
Zhang Y.
Liu K.
[J]. Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, 2021, 38 (03): : 512 - 519
[46] A Hybrid Segmental Neural Net/Hidden Markov Model System for Continuous Speech Recognition
Zavaliagkos, G.
Zhao, Y.
Schwartz, R.
Makhoul, J.
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (01): : 151 - 160
[47] Real-time traffic anomaly detection based on Gaussian mixture model and hidden Markov model
Liang, Guojun
Kintak, U.
Chen, Jianbin
Jiang, Zhiying
[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021,
[48] Partly Hidden Markov Model and its application to speech recognition
Waseda Univ, Tokyo, Japan
[J]. ICASSP IEEE Int Conf Acoust Speech Signal Process Proc, (121-124):
[49] Partly hidden Markov model and its application to speech recognition
Kobayashi, T
Furuyama, J
Masumitsu, K
[J]. ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 121 - 124
[50] DYNAMIC ADAPTATION OF HIDDEN MARKOV MODEL FOR ROBUST SPEECH RECOGNITION
GAO, YQ
CHEN, YB
WU, BX
[J]. 1989 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-3, 1989, : 1336 - 1339

← 1 2 3 4 5 →