Ch4-Speech_Signal_Representations

Ch4-Speech_Signal_Representations - Speech Recognition...

Info iconThis preview shows pages 1–15. Sign up to view the full content.

View Full Document Right Arrow Icon
Speech Recognition Speech Signal Representations
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 2 Speech Signal Representations Fourier Analysis  Discrete-time Fourier transform  Short-time Fourier transform  Discrete Fourier transform  Cepstral Analysis  The complex cepstrum and the cepstrum  Computational considerations  Cepstral analysis of speech  Applications to speech recognition  Mel-Frequency cepstral representation  Performance Comparison of Various  Representations 
Background image of page 2
February 13, 2012 Veton Këpuska 3 Discrete-Time Fourier Transform   Definition: Sufficient condition for convergence: Although  x [ n ] is discrete,  X (e j ϖ ) is continuous and periodic  with period 2 ƒ π
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 4 Discrete-Time Fourier Transform Convolution/multiplication duality:  
Background image of page 4
February 13, 2012 Veton Këpuska 5 Short-Time Fourier Analysis  (Time- Dependent Fourier Transform)  
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 6 Rectangular Window 
Background image of page 6
February 13, 2012 Veton Këpuska 7 Hamming Window 
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 8 Comparison of Windows 
Background image of page 8
February 13, 2012 Veton Këpuska 9 Comparison of Windows (cont’d) 
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 10 A Wideband Spectrogram 
Background image of page 10
February 13, 2012 Veton Këpuska 11 A Narrowband Spectrogram 
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 12 Discrete Fourier Transform  In general, the number of input points, N, and the number  of frequency samples, M, need not be the same.  If  M>N  , we must zero-pad the signal  If  M<N  , we must time-alias the signal  
Background image of page 12
February 13, 2012 Veton Këpuska 13 Examples of Various Spectral  Representations 
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Veton Këpuska 14 Cepstral Analysis of Speech  The speech signal is often assumed to be the output of an LTI system;  i.e., it is the convolution of the input and the impulse response.  If we are interested in characterizing the signal in terms of the parameters of  such a model, we must go through the process of de-convolution.  Cepstral, analysis is a common procedure used for such de-convolution.  
Background image of page 14
Image of page 15
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/11/2012 for the course ECE 5526 taught by Professor Staff during the Summer '09 term at FIT.

Page1 / 35

Ch4-Speech_Signal_Representations - Speech Recognition...

This preview shows document pages 1 - 15. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online