Speaker Identification using a Committee of Neural Networks -- A DSP based Hardware Implementation

Author

Viresh Moonasar
Ganesh K. Venayagamoorthy, Missouri University of Science and TechnologyFollow

Abstract

This paper describes the DSP (Digital Signal Processor) hardware implementation of a speaker identification system. A supervised Learning Vector Quantization (LVQ) neural network is used as the pattern classifier. Linear Predictive Coding (LPC) and Cepstral signal processing techniques are utilized to form hybrid feature parameter vectors as inputs to the pattern recognition system. The practical application of a committee of neural networks for pattern recognition rather than the conventional single-network decision system is also discussed

Recommended Citation

V. Moonasar and G. K. Venayagamoorthy, "Speaker Identification using a Committee of Neural Networks -- A DSP based Hardware Implementation," Intelligent Engineering Systems Through Artificial Neural Networks, American Society of Mechanical Engineers (ASME), Nov 2002.

Meeting Name

Artificial Neural Networks in Engineering Conference, ANNIE 2002 (2002: Nov. 10-13, St. Louis, MO)

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Digital Signal Processor; Learning Vector Quantization; Speaker Identification System

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2002 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

13 Nov 2002