ELECTRIC-ELECTRONIC ENGINEERING (ENGLISH, PHD) | |||||
PhD | TR-NQF-HE: Level 8 | QF-EHEA: Third Cycle | EQF-LLL: Level 8 |
Course Code | Course Name | Semester | Theoretical | Practical | Credit | ECTS |
EEE5540 | Speech Processing | Fall Spring |
3 | 0 | 3 | 12 |
This catalog is for information purposes. Course status is determined by the relevant department at the beginning of semester. |
Language of instruction: | English |
Type of course: | Departmental Elective |
Course Level: | |
Mode of Delivery: | Face to face |
Course Coordinator : | Dr. Öğr. Üyesi ZAFER İŞCAN |
Recommended Optional Program Components: | None |
Course Objectives: | This is an advanced level course on speech signal processing for graduate level students in Electrical and Electronics engineering. The course provides the student both the theoretical foundations of speech analysis and the detailed practical information about speech technology applications such as speech coding, speech synthesis and recognition. |
The students who have succeeded in this course; 1. Describe fundamentals of speech production mechanism and auditory perception 2. Describe basic spectral processing methods for speech signals 3. Describe linear prediction modeling of speech signals and experiment in use of linear prediction modeling in speech analysis, coding and synthesis 4. Design speech coding systems 5. Design speech synthesis systems 6. Analyze expressivity in speech signals 7. Design speech recognition systems |
Speech production mechanism and auditory perception. Spectral processing methods for speech signals. Linear prediction modeling of speech signals. Speech analysis, coding and synthesis.Expressivity in speech signals. Speech recognition systems. |
Week | Subject | Related Preparation |
1) | Basics of sound signals, auditory perception and speech production mechanism. | |
2) | Review of signal processing concepts: short-time Fourier analysis | |
3) | The Source-Filter model of speech. Overview of commonly used speech analysis software and application in recording, segmenting, viewing, analyzing speech data | |
4) | Basic speech signal parameters and estimation methods: pitch, formants, glottal flow, etc. | |
5) | Linear predictive modeling of speech signals | |
6) | Speech coding (CELP codec used in mobile communication) | |
7) | Midterm, introduction to text-to-speech synthesis. | |
8) | Text-to-speech(TTS) synthesis, basic paradigms, models | |
9) | Structure of commercial TTS systems, database design methods, systems tailored to applications. Application: create a synthesizer with your own voice | |
10) | Prosody modeling and analysis | |
11) | Analysis of expressivity, pathology and emotion in speech signals | |
12) | Homomorphic processing | |
13) | Speech recognition | |
14) | Overview of the course |
Course Notes / Textbooks: | Discrete-time processing of speech signals, John R. Deller, John H. L. Hansen, John G. Proakis, Wiley-IEEE Press, ISBN-10: 0780353862 |
References: | Theory and Applications of Digital Speech Processing, Lawrence Rabiner, Ronald Schafer, Prentice Hall, ISBN-10: 0136034284 |
Semester Requirements | Number of Activities | Level of Contribution |
Homework Assignments | 2 | % 5 |
Presentation | 1 | % 5 |
Project | 1 | % 30 |
Midterms | 1 | % 20 |
Final | 1 | % 40 |
Total | % 100 | |
PERCENTAGE OF SEMESTER WORK | % 30 | |
PERCENTAGE OF FINAL WORK | % 70 | |
Total | % 100 |
Activities | Number of Activities | Duration (Hours) | Workload |
Course Hours | 14 | 3 | 42 |
Study Hours Out of Class | 14 | 6 | 84 |
Presentations / Seminar | 1 | 10 | 10 |
Project | 1 | 20 | 20 |
Homework Assignments | 3 | 10 | 30 |
Midterms | 1 | 3 | 3 |
Final | 1 | 3 | 3 |
Total Workload | 192 |
No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
Program Outcomes | Level of Contribution |