Neural network comparison of speech recognition system using trispectrum analysis in noisy environment

Benyamin Kusumo Putro, Adi Triyanto

Research output: Contribution to journalConference article

Abstract

In this paper, a speech recognition system is developed using higher order statistic (HOS) with its fourth order of crosscorrelation (trispectrum) analysis. To analysis the distribution of the trispectrum data along its two dimensional representation, we developed an adaptive feature extraction mechanism of the trispectrum speech data based on cascade neural network that consists of SOFM (Self-Organizing Feature Map) and LVQ (Learning Vector Quantization). This cascade neural network is used as an adaptive codebook generation algorithm for determining the feature distribution of the trispectrum speech data. Two types of neural networks, namely back-propagation neural network and probabilistic neural networks, are then used as the pattern classifier of this speech recognition system. Comparison of the recognition system using those neural networks as the classifier is conducted based on sample data with and without Gaussian noise. Experimental result shown that PNN has superior recognition rate compare with that of BPNN, especially when a harsh condition of noise is added to the system.

Original languageEnglish
Pages (from-to)445-450
Number of pages6
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume4572
DOIs
Publication statusPublished - 1 Dec 2001
EventIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision - Boston, MA, United States
Duration: 29 Oct 200131 Oct 2001

Fingerprint Dive into the research topics of 'Neural network comparison of speech recognition system using trispectrum analysis in noisy environment'. Together they form a unique fingerprint.

  • Cite this