Performance Analysis of Different Wavelet Families in Recognizing Speech
Journal Title: INTERNATIONAL JOURNAL OF ENGINEERING TRENDS AND TECHNOLOGY - Year 2013, Vol 4, Issue 4
Abstract
Automatic Speech Recognition (ASR) is one of the challenging areas of research in digital signal processing and engineering due to its wide range of applications. In this paper, a speech recognition system is developed for recognizing speaker independent spoken isolated words in Malayalam. Voice signals are sampled directly from the microphone and the features are extracted using Discrete Wavelet Transforms (DWT). Different types of wavelet families are available for speech processing and mathematical analysis. Since DWT uses wavelets, the main issue here is to find out the optimal wavelets for speech recognition. This paper investigates the performance of different wavelet families like Haar, Daubechies, Symlets, Coiflets etc. A multilayer neural network trained with back propagation algorithm is used for classification. The proposed method is implemented for 1000 speakers uttering 10 isolated words each. The experimental results show different recognition accuracies for different wavelet families and the best result of 90.2% is obtained using Daubechies wavelet families with order 4
Authors and Affiliations
Sonia Sunny
Neural Network based Closed loop Speed Control of DC Motor using Arduino Uno
This paper presents the design and implementation of Arduino Uno based DC motor speed control system using Multilayer Neural Network controller and PID controller. A model reference structure is developed using PID...
Hexagonal Nonradiating Edge-Coupled Patch Configuration for Bandwidth Enhancement of Patch Antenna
For increasing the impedance bandwidth of patch antenna two novel configurations are described for the ISM band applications. A hexagonal patch structure is used in both of the configurations. First structure uses six ad...
The Comparison of Two Monopulse Tracking Systems: Four – Horn and Multimode (based on the simulation results of HFSS)
The tracking system is a functional block of satellite and navigating system that detects the presence of various electromagnetic scatterers and determines their location. During the past two decades, a considerabl...
Automatic load frequency control of multi-area power system using ANN controller and Genetic algorithm
In this paper work we analyze and design Automatic load frequency control of two areas power system using Genetic Algorithm and also for four area power system using artificial neural network (ANN), generation co...
A Framework for Pricing Schemes for Networks under Complete Information
The revenue maximization problem of service provider is considered and different pricing schemes to solve the above problem are implemented. The service provider can choose an apt pricing scheme subjected to limited reso...