COURSE SYLLABUS

DIGITAL SPEECH PROCESSING

1	Course Title:	DIGITAL SPEECH PROCESSING
2	Course Code:	EEM5705
3	Type of Course:	Optional
4	Level of Course:	Second Cycle
5	Year of Study:	1
6	Semester:	1
7	ECTS Credits Allocated:	6
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:	None
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Doç. Dr. FİGEN ERTAŞ
16	Course Lecturers:
17	Contactinformation of the Course Coordinator:	E-posta:fertas@uludag.edu.tr Tel: (224) 294 2017 Adres: Elektrik-Elektronik Mühendisliği Bölümü, 5.Kat, No:524
18	Website:
19	Objective of the Course:	The aim of this couse is to expose students to the properties of speech signals and its nature in time and frequency domain, and to help them gain ability to apply basic signal processing methods on speech signals.
20	Contribution of the Course to Professional Development	To help students gain ability to collect, process, analyse, and interpret data.

Learning Outcomes:

1	Gain the ability to model and solve speech and audio signal processing problems using theoretical and practical knowledge.;
2	Gain the ability to identify, model, and solve speech and audio signal processing problems; the ability to select and apply appropriate analysis and modelling methods for these problems.;
3	Gain the ability to design partly or fully a complex system, process, device or a product in speech and audio signal processing fields meeting specific requirements under realistic constraints and conditions; the ability to apply modern design methods in this context.;
4	Gain the ability to develop, select, and use modern techniques and tools necessary for speech and audio signal processing applications; the ability to use information technologies in an efficient way.;
5	Gain the ability to design and conduct complex experiments and to collect, analyze and interpret data for speech and audio signal processing problems;

22	Course Content:

Week	Theoretical	Practical
1	Quick rewiev of signal processing methods, General concepts of digital signal Processing
2	Fundamentals of digital speech signal processing
3	Production & classification of speech sounds, digital models for speech production
4	time-domain analysis methods
5	short-time spectrum analysis
6	linear prediction analysis (LPC) methods
7	pitch detection
8	Formant Tracking
9	Mel Frequency Cepstrum Coefficients (MFCC)
10	Detailed review of Speech Signal Processing Applications (speech rec., language rec., gender rec., speaker rec., emotion rec., etc.)
11	dynamic time warping
12	Hidden Markov Models (HMM).
13	Vector Quantization
14	Text-independent speaker recognition using VQ example

23	Textbooks, References and/or Other Materials:	1. Theory and Applications of Digital Speech Processing, L. Rabiner, Prentice Hall, 2010 2. Digital Processing of Speech Signals, Rabiner & R.W. Schafer, Prentice Hall, 1978 3. Fundamentals of Speech Recognition, Rabiner & B.-H. Juang, Prentice Hall, 1993 4. Discrete-Time Processing of Speech Signals J. Deller, J. H. Hansen & J. G. Proakis, Wiley-IEEE Press, 1993 5. Digital Speech Processing, Synthesis and Recognition, 2nd Ed., S. Furui, CRC Press, 2000
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	1	30
Quiz	1	5
Homeworks, Performances	1	5
Final Exam	1	60
Total	4	100
Contribution of Term (Year) Learning Activities to Success Grade		40
Contribution of Final Exam to Success Grade		60
Total		100
Measurement and Evaluation Techniques Used in the Course	Measurement and evaluation are performed according to the Rules & Regulations of Bursa Uludağ University on Postgraduate Education.
Information	1 midterm 1 final exam and 1 quiz is conducted in combination with 1 homework, and graded by using University's relative evaluation system.

ECTS / WORK LOAD TABLE

CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High