Embedded Speech Recognition System Design and Optimization

被引：4

作者：

Chen Yehui ^{[1
]}

Wang Enliang ^{[1
]}

Ji Liqin ^{[1
]}

机构：

[1] Anhui Xinhua Univ, Elect Commun Engn Coll, Hefei 230088, Peoples R China

来源：

PROCEEDINGS 2016 EIGHTH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION ICMTMA 2016 | 2016年

关键词：

embedded speech recognition; hidden Markov model; S3C2440;

D O I：

10.1109/ICMTMA.2016.72

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The speech recognition implementation in embedded systems is influenced by many factors. In embedded systems environment, computing rate is relatively lower, storage space is limited. Although the speech recognition technology has won some achievement in high performance platform, it's necessary to do further analysis and research on speech recognition in embedded platform. Speech recognition hardware system is constructed and high performance processor S3C2440 is taken as the key processing unit. Peripheral devices are also described in detail. In order to realize speech recognition algorithm, hidden Markov algorithm is investigated. Then embedded speech recognition software system is constructed based on Linux. After testing validation, this system has high recognition speed and accurate recognition rate, which realizes the speech recognition function. The system has good feasibility and practicability. According to the specific requirements of practical application, it can be used in vehicle terminal system, smart home system and entrance guard system, etc.

引用

页码：266 / 269

页数：4

共 16 条

[1] Improvement of the speech recognition in noisy environments using a nonparametric regression [J].

Amrouche, A. ;

Taleb-Ahmed, A. ;

Rouvaen, J. M. ;

Yagoub, M. C. E. .

INTERNATIONAL JOURNAL OF PARALLEL EMERGENT AND DISTRIBUTED SYSTEMS, 2009, 24 (01) :49-67

[2] A computer model of auditory efferent suppression: Implications for the recognition of speech in noise [J].

Brown, Guy J. ;

Ferry, Robert T. ;

Meddis, Ray .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2010, 127 (02) :943-954

[3]

Hanpu Jiang jie, 2010, COMPUTER TECHNOLOGY, V20, P245

[4] Power Function-Based Power Distribution Normalization Algorithm for Robust Speech Recognition [J].

Kim, Chanwoo ;

Stern, Richard M. .

2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, :188-+

[5]

Kim C, 2009, INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, P28

[6]

Lee W, 2003, ESA'03: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON EMBEDDED SYSTEMS AND APPLICATIONS, P132

[7] Efficient blind system identification of non-Gaussian autoregressive models with HMM modeling of the excitation [J].

Li, Chunjian ;

Andersen, Soren Vang .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2007, 55 (06) :2432-2445

[8] Speech Recognition Approach Based on Speech Feature Clustering and HMM [J].

Li, XinGuang ;

Yao, MinFeng ;

Yang, JiaNeng .

JOURNAL OF COMPUTERS, 2012, 7 (09) :2269-2275

[9] HMM/ANN hybrid model for continuous Malayalam speech recognition [J].

Mohamed, Anuj ;

Nair, K. N. Ramachandran .

INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY AND SYSTEM DESIGN 2011, 2012, 30 :616-622

[10] Combining evidence from residual phase and MFCC features for speaker recognition [J].

Murty, KR ;

Yegnanarayana, B .

IEEE SIGNAL PROCESSING LETTERS, 2006, 13 (01) :52-55

← 1 2 →