ad 2

Monday, September 23, 2013

SPEECH PROCESSING(SEMESTER VIII)

ANNA UNIVERSITY :: CHENNAI 600 025
UNIVERSITY DEPARTMENTS
REGULATIONS – 2008
CURRICULUM FROM III TO VIII SEMESTERS AND ELECTIVES FOR
B.TECH. INFORMATION TECHNOLOGY


SPEECH PROCESSING

UNIT I

MECHANICS OF SPEECH

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

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

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

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

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

No comments:

Post a Comment