Speaker Identification Using a Committee of Neural Networks - a DSP Based Hardware Implementation
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
V. Moonasar and G. K. Venayagamoorthy, "Speaker Identification Using a Committee of Neural Networks - a DSP Based Hardware Implementation," ANNIE 2002, American Society of Mechanical Engineers (ASME), Jan 2002.
Electrical and Computer Engineering
Keywords and Phrases
Digital Signal Processor; Learning Vector Quantization; Speaker Identification System
Article - Conference proceedings
© 2002 American Society of Mechanical Engineers (ASME), All rights reserved.