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

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Speech Recognition Speech Signal Representations February 11, 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 February 11, 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 . February 11, 2012 Veton Këpuska 4 Discrete-Time Fourier Transform Convolution/multiplication duality: February 11, 2012 Veton Këpuska 5 Short-Time Fourier Analysis (Time- Dependent Fourier Transform) February 11, 2012 Veton Këpuska 6 Rectangular Window February 11, 2012 Veton Këpuska 7 Hamming Window February 11, 2012 Veton Këpuska 8 Comparison of Windows February 11, 2012 Veton Këpuska 9 Comparison of Windows (cont’d) February 11, 2012 Veton Këpuska 10 A Wideband Spectrogram February 11, 2012 Veton Këpuska 11 A Narrowband Spectrogram February 11, 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 February 11, 2012 Veton Këpuska 13 Examples of Various Spectral Representations February 11, 2012 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. February 11, 2012...
View Full Document

{[ snackBarMessage ]}

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