Integrated system for speech recognition & voice recognition using DSP and neural networks

Ace p.

Order the writing of a tailor-made Physics Term papers

Free quote online

Thesis Format .pdf

Integrated system for speech recognition & voice recognition using DSP and neural networks

Download

Read an extract

Reader
Abstract
Contents
Extract

Abstract

Neural Networks find great application in the field of signal processing. Here in this paper too we have proposed a simple algorithm to achieve better efficiency in speech recognition and also capable of distinguishing between male and female voices. Speech recognition is the process of automatically recognizing the speaker on the basis of individual information included in speech signals. There are many possibilities for discrete representation of speech signals. As shown in the below figure, these representations can be classified into two broad groups, namely wave form representations and parametric representations.

Abstract
Introduction
Classification of speech recognition
Representation of speech signals
Tools for speech recognition
Signal analysis method
Speech parameters
Formants
Pitch
Implementation of the system
Euclidean distance calculation
Results of system
Neural network based decision making
Results from the neural network decision
Conclusion
References

Get this table of contents for free after login.

Extract

[...] Euclidean Distance Calculation Neural Network based Decision Making Euclidean Distance Calculation Here the dynamic input of a speaker whose voice in the data base are compared with the templates stored for verification, the comparison is done by calculating the Euclidean distance for the calculated parameters. The Euclidean Distance is calculated as below, EDN (variance-person12 + . variance-personN2 ) + (pitch-person12 + . pitch-personN2 ) + National Conference on Emerging Trends in Computing and Communication (ETCC-2008) REFERENCES 1. L.R. Rabiner and R.W. [...]

[...] Here in this paper too we have proposed a simple algorithm to achieve better efficiency in speech recognition and also capable of distinguishing between male and female voices Tools for Speech Recognition Speech recognition at its most elementary level comprises a collection of algorithms drawn from a wide variety of disciplines, including statistical pattern recognition, communication theory, signal processing and linguistics among others. This parametric representation is then used for further analysis and process using following signal processing tools, Signal Analysis Method Representation of Speech Signals There are many possibilities for discrete representation of speech signals. [...]

[...] Flanagan: Speech Anaysis Synthesis and Perception 2nd Edition Sprenger Vertag John G Proakis & Dimitary G Malolakis: Digital Signal Processing, 3rd Edition, PHI Lawrence R Rabiner and Bernald Gold: Theory Applications of Digital Signal Processing, PHI Features Extracted for Person 2 (Female) 5. Sanjith K. Mithra: Digital Signal Processing A Computer Based approach, TMH www.speech.cs.cmu.edu www.mathworks.nl/access/helpdesk/help Neural Network based Decision Making The obtained values are then fed as input to a Neural Network that processes on these values and decisions. [...]

pdf