CE827 Speech and Audio Processing

Course Name: 

CE827 Speech and Audio Processing

Programme: 

M.Tech (CE)

Category: 

Elective (Ele)

Credits (L-T-P): 

(3-0-0)3

Content: 

Speech Production – human speech production mechanism, acoustic theory of speech production, digital models for speech production. Speech perception – human hearing, auditory psychophysics, JND, pitch perception, auditory masking, models for speech perception. Speech Analysis – Time and frequency domain analysis of speech, speech parameter estimation, Linear prediction. Speech compression – quality measures, waveform coding, source coders, Speech compression standards for personal communication systems. Audio processing – characteristics of audio signals, sampling, Audio compression techniques, Standards for audio compression in multimedia applications, MPEG audio encoding and decoding, audio databases and applications. Speech synthesis – text to speech synthesis, letter to sound rules, syntactic analysis, timing and pitch segmental analysis. Speech recognition – Segmental feature extraction, DTW, HMMs, approaches for speaker, speech and language recognition and verification.

References: 

Douglas O’Shaugnessy, Speech Communication – Human and Machine, IEEE Press, 2000
L R Rabiner, Digital Processing of Speech Signals, Pearson,1978
T.F Quatieri , Discrete-time speech signal processing: Principles and Practise Pearson,2002
Zi Nian Li, Fundamentals of Multimedia, Pearson Education, 2003
 

Contact us

Dr. U. Shripathi Acharya,  Professor and Head, 
Department of E&C, NITK, Surathkal
P. O. Srinivasnagar,
Mangalore - 575 025 Karnataka, India.

  • Hot line: +91-0824-2473046

Connect with us

We're on Social Networks. Follow us & get in touch.