CP5096 SPEECH PROCESSING AND SYNTHESIS SYLLABUS - ANNA UNIVERSITY PG REGULATION 2017

CP5096 SPEECH PROCESSING AND SYNTHESIS SYLLABUS

REGULATION 2017

ME CSE - SEMESTER 3

OBJECTIVES:

• To understand the mathematical foundations needed for speech processing
• To understand the basic concepts and algorithms of speech processing and synthesis
• To familiarize the students with the various speech signal representation, coding and recognition techniques
• To appreciate the use of speech processing in current technologies and to expose the students to real– world applications of speech processing

UNIT I FUNDAMENTALS OF SPEECH PROCESSING
Introduction – Spoken Language Structure – Phonetics and Phonology – Syllables and Words – Syntax and Semantics – Probability, Statistics and Information Theory – Probability Theory – Estimation Theory – Significance Testing – Information Theory.

UNIT II SPEECH SIGNAL REPRESENTATIONS AND CODING
Overview of Digital Signal Processing – Speech Signal Representations – Short time Fourier Analysis – Acoustic Model of Speech Production – Linear Predictive Coding – Cepstral Processing – Formant Frequencies – The Role of Pitch – Speech Coding – LPC Coder.

UNIT III SPEECH RECOGNITION
Hidden Markov Models – Definition – Continuous and Discontinuous HMMs – Practical Issues – Limitations. Acoustic Modeling – Variability in the Speech Signal – Extracting Features – Phonetic Modeling – Adaptive Techniques – Confidence Measures – Other Techniques.

UNIT IV TEXT ANALYSIS
Lexicon – Document Structure Detection – Text Normalization – Linguistic Analysis – Homograph Disambiguation – Morphological Analysis – Letter-to-sound Conversion – Prosody – Generation schematic – Speaking Style – Symbolic Prosody – Duration Assignment – Pitch Generation

UNIT V SPEECH SYNTHESIS
Attributes – Formant Speech Synthesis – Concatenative Speech Synthesis – Prosodic Modification of Speech – Source-filter Models for Prosody Modification – Evaluation of TTS Systems.

TOTAL : 45 PERIODS

OUTCOMES:
Upon completion of this course, the students should be able to

• Identify the various temporal, spectral and cepstral features required for identifying speech units – phoneme, syllable and word 
• Determine and apply Mel-frequency cepstral coefficients for processing all types of signals
• Justify the use of formant and concatenative approaches to speech synthesis
• Identify the apt approach of speech synthesis depending on the language to be processed
• Determine the various encoding techniques for representing speech.

REFERENCES:

1. Joseph Mariani, ―Language and Speech Processing‖, Wiley, 2009.
2. Lawrence Rabiner and Biing-Hwang Juang, ―Fundamentals of Speech Recognition‖, Prentice Hall Signal Processing Series, 1993.
3. Sadaoki Furui, ―Digital Speech Processing: Synthesis, and Recognition, Second Edition, (Signal Processing and Communications)‖, Marcel Dekker, 2000.
4. Thomas F.Quatieri, ―Discrete-Time Speech Signal Processing‖, Pearson Education, 2002.
5. Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, ―Spoken Language Processing – A guide to Theory, Algorithm and System Development‖, Prentice Hall PTR, 2001.