19-03-2011, 10:24 AM
presented by:
Shyam Sundar Rath
[attachment=10547]
Why Speech Recognition ?
Decrease the human intervention in different processes or in other words automate them.
Security and privacy of documents.
DSP in Speech Recognition
DSP has its own functions in Mat lab for Speech Recognition.
Provides best quality of voice processing.
➌ Offers various options like
DFT
STFT
SCFT
DWT
Challenges in speech Recognition
Human speech parameterized by different variables which vary from speaker to speaker.
Speech signal consists of both vowels and consonants.
Speech signal is not stationary.
Languages vary the speech.
Approaches
Feature Extraction.
Frequency domain analysis.
FT
Projects signals onto complex sines and cosines, infinitely long signals
WT
Carries both temporal location - like an impulse - and frequency content - like a sinusoid.
Conception of wavelets
➊ Wavelets are localized waves and have their energy concentrated in time.
➋ “Wave” means Oscillatory and “let” means Quick decaying.
➌ Difference between wave and wavelet :-
Wavelet Transform
➊ Wavelet transform decomposes a signal into a set of basis functions.
Wavelets are obtained from a single prototype wavelet y(t) called mother wavelet by dilations and shifting
Then what is DWT
Discrete wavelet transform (DWT), which transforms a discrete time signal to a discrete wavelet representation.
Equation of a discrete mother wavelet
Daubechies wavelet transform :-
➊ An orthonormal, compactly supported family of wavelets.
➋ Calculated using the scaling functions and wavelet functions.
➌ Is the default wavelet transform present in mat lab.
Shyam Sundar Rath
[attachment=10547]
Why Speech Recognition ?
Decrease the human intervention in different processes or in other words automate them.
Security and privacy of documents.
DSP in Speech Recognition
DSP has its own functions in Mat lab for Speech Recognition.
Provides best quality of voice processing.
➌ Offers various options like
DFT
STFT
SCFT
DWT
Challenges in speech Recognition
Human speech parameterized by different variables which vary from speaker to speaker.
Speech signal consists of both vowels and consonants.
Speech signal is not stationary.
Languages vary the speech.
Approaches
Feature Extraction.
Frequency domain analysis.
FT
Projects signals onto complex sines and cosines, infinitely long signals
WT
Carries both temporal location - like an impulse - and frequency content - like a sinusoid.
Conception of wavelets
➊ Wavelets are localized waves and have their energy concentrated in time.
➋ “Wave” means Oscillatory and “let” means Quick decaying.
➌ Difference between wave and wavelet :-
Wavelet Transform
➊ Wavelet transform decomposes a signal into a set of basis functions.
Wavelets are obtained from a single prototype wavelet y(t) called mother wavelet by dilations and shifting
Then what is DWT
Discrete wavelet transform (DWT), which transforms a discrete time signal to a discrete wavelet representation.
Equation of a discrete mother wavelet
Daubechies wavelet transform :-
➊ An orthonormal, compactly supported family of wavelets.
➋ Calculated using the scaling functions and wavelet functions.
➌ Is the default wavelet transform present in mat lab.