| Course Type | Elective Course |
|---|
| Course Level | Master's Degree With Thesis |
|---|
| Year of Study | - |
|---|
| Semester | - |
|---|
| ECTS | 10 |
|---|
| Name of Lecturer(s) |
|
| Learning Outcomes |
At the end of this course, the students;
- Know automata theory and general concepts.
- Describe finite-state transducers.
- Describes weighted automata algorithms.
- Know speech recognition models.
- Apply text-to-speech methods.
- Apply the tecniques learned in an engineering problem.
|
| Mode of Delivery | Face to face |
|---|
| Prerequisites | No |
|---|
| Recommended Optional Programme Components | None |
|---|
| Course Description | Introduction to speech recognition and introduction to the theory of automata. Automata-theoretic foundations.Introduction to the finite-state software tools. Rational relations. Transductions and weighted finite-state transducers.Weighted automata algorithms. Shortest-paths algorithms. Speech recognition by composition of weighted transducers.Models in speech recognition. Large vocabulary speech recognition. Text-to-speech |
|---|
| Course Contents |
| WEEK |
TOPICS |
|
1st Week |
Introduction to speech recognition and introduction to the theory of automata |
|
2nd Week |
Automata-theoretic foundations |
|
3rd Week |
Introduction to the finite-state software tools |
|
4th Week |
Rational relations |
|
5th Week |
Rational relations |
|
6th Week |
Transductions and weighted finite-state transducers |
|
7th Week |
Weighted automata algorithms |
|
8th Week |
Mid-term |
|
9th Week |
Shortest-paths algorithms |
|
10th Week |
Speech recognition by composition of weighted transducers |
|
11th Week |
Speech recognition by composition of weighted transducers |
|
12th Week |
Models in speech recognition |
|
13th Week |
Large vocabulary speech recognition |
|
14th Week |
Text-to-speech |
|
| Recommended or Required Reading | 1. Rabiner, L.R., Schafer, R.W., "Digital Processing of Speech Signals" Pearson Higher Education, (2011)
2. Rabiner, L.R., Juand, B.H., "Fundamentals of Speech Recognition", Prentice Hall, (1993)
3. Jelinek, F., "Statistical Methods For Speech Recognition", MIT Press, (1998)
|
|---|
| Planned Learning Activities and Teaching Methods |
- Lecture
- Questions/Answers
- Presentation
- Practice
- Problem Solving
- Project
- Report Preparation
|
|---|
| Assessment Methods and Criteria |
|
Quantity |
Percentage (%) |
| Mid-term |
1 |
30 |
| Assignment |
1 |
15 |
| Project |
1 |
15 |
| Total(%) |
|
60 |
| Contribution of In-term Studies to Overall Grade(%) |
|
60 |
| Contribution of Final Examination to Overall Grade(%) |
|
40 |
| Total(%) |
|
100 |
|
| ECTS Allocated Based on Student Workload |
| Activities |
Quantity |
Duration (Hour) |
Total Workload (Hour) |
| Midterm exam |
1 |
2 |
2 |
| Preparation for Quiz |
|
|
|
| Individual or group work |
14 |
11 |
154 |
| Preparation for Final exam |
1 |
69 |
69 |
| Course hours |
14 |
3 |
42 |
| Preparation for Midterm exam |
1 |
44 |
44 |
| Laboratory (including preparation) |
|
|
|
| Final exam |
1 |
2 |
2 |
| Homework |
|
|
|
| Total Work Load | 313 |
| Total Work Load / 30 (h) | 10.43 |
| ECTS Credit of the Course | 10 |
|
| Language of Instruction | Turkish |
|---|
| Work Placement(s) | No |
|---|
