IT2064 SPEECH SIGNAL PROCESSING Syllabus

IT2064  SPEECH SIGNAL PROCESSING  Syllabus

IT2064           SPEECH SIGNAL PROCESSING                     L  T  P  C  
                                                                                                                   3   0   0  3

UNIT I     MECHANICS OF SPEECH                     9
Speech  production:  Mechanism  of  speech  production,  Acoustic  phonetics  -  Digital
models  for  speech  signals  -  Representations  of  speech  waveform:  Sampling  speech
signals,  basics  of  quantization,  delta  modulation,  and  Differential  PCM  -  Auditory
perception:  psycho acoustics.

UNIT II   TIME DOMAIN METHODS FOR SPEECH PROCESSING             9
Time  domain  parameters  of  Speech  signal  –  Methods  for  extracting  the  parameters
Energy,  Average Magnitude,  Zero  crossing  Rate  –  Silence  Discrimination  using  ZCR
and energy – Short Time Auto Correlation Function – Pitch period estimation using Auto
Correlation Function.

UNIT III   FREQUENCY DOMAIN METHOD FOR SPEECH PROCESSING           9
Short  Time  Fourier  analysis:  Fourier  transform  and  linear  filtering  interpretations,
Sampling  rates  - Spectrographic  displays  - Pitch  and  formant extraction  - Analysis  by
Synthesis  -  Analysis  synthesis  systems:  Phase  vocoder,  Channel  Vocoder  -
Homomorphic  speech  analysis:  Cepstral  analysis  of  Speech,  Formant  and  Pitch
Estimation, Homomorphic Vocoders.

UNIT IV   LINEAR PREDICTIVE ANALYSIS OF SPEECH                         9
Basic  Principles  of  linear  predictive  analysis  –  Auto  correlation method  – Covariance
method – Solution of LPC equations – Cholesky method – Durbin’s Recursive algorithm
–  Application  of  LPC  parameters  – Pitch  detection  using  LPC  parameters  –  Formant
analysis – VELP – CELP.



UNIT V   APPLICATION OF SPEECH & AUDIO SIGNAL PROCESSING         9
Algorithms:  Dynamic  time  warping,  K-means  clustering  and  Vector  quantization,
Gaussian mixture modeling, hidden Markov modeling  - Automatic Speech Recognition:
Feature  Extraction  for  ASR,  Deterministic  sequence  recognition,  Statistical  Sequence
recognition, Language models - Speaker identification and verification – Voice response
system  –  Speech  synthesis:  basics  of  articulatory,  source-filter,  and  concatenative
synthesis – VOIP

TEXT BOOKS:
1.  L. R. Rabiner and R. W. Schaffer,  “Digital Processing of Speech signals”, Prentice
Hall, 1978.
2.  Ben Gold and Nelson Morgan,  “Speech and Audio Signal Processing”, John Wiley
and Sons Inc., Singapore,  2004.

REFERENCES:
1.  Quatieri, “Discrete-time Speech Signal Processing”, Prentice Hall, 2001.
2.  L.R. Rabiner and B. H. Juang, “Fundamentals of speech recognition”, Prentice Hall,
1993.