Recognition of Aircraft Engine Sound Based on GMM-UBM Model

被引：1

作者：

Yuan, Shuai ^{[1
]}

Sun, Chengli ^{[2
]}

Yang, Haoge ^{[2
]}

机构：

[1] Sci & Technol Avion Integrat Lab, Shanghai, Peoples R China

[2] Hangkong Univ, Informat Sch, Nanchang, Jiangxi, Peoples R China

来源：

2017 INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING (EITCE 2017) | 2017年 / 128卷

关键词：

Speaker Recognition; GMM-UBM; MFCC; Abnormal sound detection; MAP; SPEECH;

D O I：

10.1051/matecconf/201712805011

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Gaussian mixture model-universal background model (GMM-UBM) is a commonly-used speaker recognition technology, and which has achieved good effect for detection speaker's sound. In this paper, we explore GMM-UBM method for use with abnormal aircraft engine sound detection. We designed a GMM-UBM based aircraft engine sound recognition system, which extracts MFCC feature parameters and trains the GMM-UBM models using maximum a posteriori (MAP) adaptive algorithm. Experimental results show the GMM-UBM based aircraft engine sound recognition system can achieve higher recognize rate in real-word aircraft engine sound test.

引用

页数：4

共 18 条

[11] An Adaptive Framework for Acoustic Monitoring of Potential Hazards
Ntalampiras, Stavros
Potamitis, Ilyas
Fakotakis, Nikos
[J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2009,
[12] Radhakrishnan R, 2005, SPIE IMAGE VIDEO COM
[13] Wang B., 2005, PRACTICAL FUNDAMENTA
[14] N-channel hidden Markov models for combined stressed speech classification and recognition
Womack, BD
Hansen, JHL
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1999, 7 (06): : 668 - 677
[15] Xiaoyun LV, 2010, RES ABNORMAL AUDIO R
[16] Ye Jianjie, 2014, DESIGN IMPLEMENTATIO
[17] Zhang Zhengping, 2016, COMMUNICATION POWER, V33
[18] Zhou X, 2008, LECT NOTES COMPUT SC, V4625, P345

← 1 2 →