Speech Processing and Recognition
Description: Study of speech signals, their properties, and the digital
processing thereof to recover these properties.
Textbook: L.R. Rabiner & R.W. Schafer, Digital Processing of Speech Signals,
Prentice-Hall, NY, 1978.
Reference: T.P. Barnwell, et al, Speech Coding, Georgia Tech, 1996.
L. Rabiner & B.H. Juang, Fundamentals of Speech Recognition,
Prentice-Hall, NY, 1993.
Chapter Topic
1 Introduction. Speech, its processing, and some applications.
2 Fundamentals of speech processing. Analysis tools including
z, Fourier, and DFT transforms; FIR and IIR filters; sampling.
3 Digital models for the speech signal. Vocal tract analog
and digital models.
4 Time Domain models for speech processing. Useful performance
measures including energy, zero-crossings, voiced and unvoiced,
pitch periods, correlation functions, and smoothing.
5 Digital representations of the speech waveform. Encoding of
speech using delta modulation, PCM and differential PCM, other
systems.
6 Short-time Fourier analysis. Short term analysis effects,
filter banks, pitch detection, and vocoders.
7 Homomorphic speech processing. Cepstrum, pitch detection,
formant estimation, and vocoders.
8 Linear predictive coding of speech. LPC methods and parameters,
relations between speech parameters.
9 Digital speech processing for man-machine communication by voice.
Speech and speaker recognition, and voice response systems.
Laboratory Projects: Design, analyze, and test speech recognition algorithms
of standard library signals.
Return to Workshops