EC354

Speech Processing

Pre-Requisite :EC201 and EC202
Contact Hours and Credits : ( 3 -0- 0 ) 3

Objective : 

The purpose of this course is to explain how DSP techniques could be used for solving problems in speech communication.

Topics Covered :

Phonetic Representation of speech - Models of Speech production - Perception of Loudness - Critical bands - Pitch perception - Auditory masking.

Short time Energy and Zero-crossing rate - Short time Autocorrelation function - Short Time Fourier transform - The speech spectrogram - Relation of STFT to STACF with speech signals .Shot-Time Cepstrum - Shot time Homo morphic Filtering of Speech signal - Application to pitch detection and Pattern recognition.

Linear prediction and the speech model - Computing the prediction co-efficient-LPC spectrum - Applications to speech compression and pattern recognition.

Digital speech coding - Closed loop coders-Open loop coders - Frequency domain coders. Text to Speech (TTS) analysis - Evolution of speech synthesis systems - Unit selection methods - TTS Applications.

Automatic speech recognition (ASR) - The Decision processes in ASR - Representative recognition performance - Principle Component Analysis- Singular Value Decomposition - Usage of Artificial Intelligence and Linear algebra in Speech processing.

Course Outcomes :

Students are able to

  • CO1: Illustrate how the speech production  is modeled 
  • CO2: Summarize the various techniques involved in collecting the features from the speech signal in both time and frequency domain
  • CO3: Compare the various techniques involved in speech and speaker detection
  • CO4: Summarize the various speech compression techniques

Text Books:

  • Lawrence R. Rabiner and Ronald. W. Schafer: Introduction to Digital speechprocessing, now publishers USA, 2007.
  • E.S. Gopi: Algorithm collections for digital signal processing using matlab, Springer, 2007.

Reference Books:

  • L.R. Rabiner and R.W. Schafer: Digital processing of speech signals, Prentice Hall,1978
  • T.F. Quatieri: Discrete-time Speech Signal Processing, Prentice-Hall, PTR, 2001
  • L. Hanzaetal, Voice Compression and Communications, Wiley/ IEEE , 2001.