Scribd Logo
Upload

Welcome to Scribd!

  • 67 views

    Development of A Novel Voice Verification System Using Wavelets

    Uploaded by

    Babu Shaik
    This document describes the development of a novel voice verification system using wavelets. The system aims to employ wavelets to study the dynamic properties of voice signals. It uses a combination of RASTA filtering and LPC analysis. Wavelet decomposition is used to extract features from the voice signals. Initial results show the system can accurately verify individuals based on their voice around 75-80% of the time. The system's accuracy could be improved by incorporating hidden Markov models.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd

    Development of A Novel Voice Verification System Using Wavelets

    Uploaded by

    Babu Shaik
    67 views22 pages
    This document describes the development of a novel voice verification system using wavelets. The system aims to employ wavelets to study the dynamic properties of voice signals. It uses a combination of RASTA filtering and LPC analysis. Wavelet decomposition is used to extract features from the voice signals. Initial results show the system can accurately verify individuals based on their voice around 75-80% of the time. The system's accuracy could be improved by incorporating hidden Markov models.

    Original Description:

    Original Title

    novel_voice_ppt

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document describes the development of a novel voice verification system using wavelets. The system aims to employ wavelets to study the dynamic properties of voice signals. It uses a combination of RASTA filtering and LPC analysis. Wavelet decomposition is used to extract features from the voice signals. Initial results show the system can accurately verify individuals based on their voice around 75-80% of the time. The system's accuracy could be improved by incorporating hidden Markov models.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    67 views22 pages

    Development of A Novel Voice Verification System Using Wavelets

    Uploaded by

    Babu Shaik
    This document describes the development of a novel voice verification system using wavelets. The system aims to employ wavelets to study the dynamic properties of voice signals. It uses a combination of RASTA filtering and LPC analysis. Wavelet decomposition is used to extract features from the voice signals. Initial results show the system can accurately verify individuals based on their voice around 75-80% of the time. The system's accuracy could be improved by incorporating hidden Markov models.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 22

    DEVELOPMENT OF A NOVEL VOICE

    VERIFICATION SYSTEM USING


    WAVELETS
    AIM OF THE PROJECT

    The aim of the project is to study The Voice


    Recognition Using Wavelet Feature
    Extraction employ wavelets in voice
    recognition for studying the dynamic
    properties and characteristics of the voice
    signal.
    INTRODUCTION
     The developed voice recognition system is word
    dependant voice verification system combining the
    RASTA and LPC.
     The voice signal is filtered using the special
    purpose voice signal filter using the Relative
    Spectral Algorithm (RASTA)
     The signals are denoised and decomposed to derive
    the wavelet coefficients and thereby a statistical
    computation is carried out.
    CONT....
     the accuracy of the verifying sample individual
    voice to his own voice is quite high (around 75%
    to 80%).
     The reliability of the signal verification is
    strengthened by combining entailments from
    these two completely different aspectsof the
    individual voice.
    CONT....
     For voice comparison purposes four out five
    individuals are verified and the results show
    higher percentage of accuracy.
     The accuracy of the system can be improved by
    incorporating advanced pattern recognition
    techniques such as Hidden Markov Model
    (HMM).
    WAVELETS
     Data

     Time domain

     Frequency domain
    FOURIER TRANSFORMS
     The Great Father Fourier - Fourier Transforms
    Any Periodic function can be expressed as linear
    combination of basic trigonometric functions
    (Basis functions used are sine and cosine)


    X(f )   x (t )e  2ift dt
    

    x(t )   X ( f )e 2ift
    df
    
    COSINE AND SINE PARTS
     Real part
    and imaginary
    part

    x(t )  a0 / 2   a f cos( ft )  b f sin( ft )


    DRAWBACKS

    Integration from -inf to +inf


    Gives frequency content of total time series but temporal information is
    lost!
    SHORT TIME FOURIER TRANSFORMS

    Same as usual Fourier transforms, but data is modified by


    multiplication with a window function
    Only part of data at a time is taken and processed
    DRAWBACKS OF STFT
     Frequency and time resolutions are fixed
    (Wider the window width, lesser the time resolution and
    more the frequency resolution and vice versa)

     As frequency resolution increases, time resolution


    decreases – uncertainty principle
     Desired: Good time resolution at high frequencies
    and good frequency resolution at low
    frequencies!
    WHAT ARE WAVELETS?
     A small wave
     Extends to finite interval
    SOME MATHEMATICAL EXPRESSIONS

    1   t  
    W ( , s ) 
    s  x(t )  s dt

    x(t) actual time series


    (t) wavelet function

    Integrable and limited to finite region



      (t )dt  0
    
    Total energy finite

      (t )  dt  
    2
    
    TYPICAL PICTURE
    1D WAVELET TRANSFORM
    RASTA (RELATIVE SPECTRAL ALGORITHM)

     This method works by applying a band-pass filter


    to the energy in each frequency sub-band in order
    to smooth over short-term noise variations and to
    remove any constant offset.
     stationary noises are often detected. Stationary
    noises are noises that are present for the
    fullperiod of a certain signal and does not have
    diminishing feature
    CONT..
     The assumption that needs to bemade is that the
    noise varies slowly with respect to speech.
     This makes the RASTA a perfect tool to be
    included in the initial stages of voice signal
    filtering to remove stationary noises
     The stationary noises that are identified are
    noises in the frequency range of 1Hz - 100Hz.
    SYSTEM IMPLEMENTATION
    RESULTS
    CONT...
    CONCLUSION
     The Voice Recognition Using Wavelet Feature Extraction
    employ wavelets in voice recognition for studying the
    dynamic properties and characteristics ofthe voice signal. The
    voice recognition system that is developed is word dependant
    voice verification system used to verify the identity of an
    individual based on their own voice signal using the
    statistical computation, formant estimation and wavelet
    energy.. By using the fifty preloaded voice signals from five
    individuals, the verification tests have been carried and an
    accuracy rate of approximately 80 % has been achieved
    THANK YOU

    You might also like