Information Package / Course Catalogue
Automatic Speech Recognition and Synthesis
Course Code: MTK639
Course Type: Area Elective
Couse Group: Third Cycle (Doctorate Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 3
Prt.: 0
Credit: 3
Lab: 0
ECTS: 8
Objectives of the Course

In this course, the subjects of Speech Recognition and Synthesis will be taught and the applications about the course will be developed. Firstly, speech production and acoustic modeling will be presented. Then, The methods of Speech Recognition and Synthesis will be explained.

Course Content

Acoustic Theory of Speech Production, Human hearing, acoustics, and phonetics. Signal Representation, Vector Quantization. Speech spectrum analysis (Fourier analysis, cepstral analysis, spectrogram reading). Fundamental frequency analysis (F0 estimation, prosody models). Speech synthesis. Linear Prediction (all-pole model, LPC, PARCOR, LSP analysis). Learning algorithms and application (Viterbi algorithm, Bayes’ Theorem). Speech coding (waveform coding, PCM, LPC). Dynamic time warping and acoustic modeling. Hidden Markov Modeling, expectation-maximization, and search. Language Modeling. Graphical Models. Segment-Based ASR, Finite State Transducers.

Name of Lecturer(s)
Learning Outcomes
1.Ability to understand the concepts of Speech Recognition and Synthesis
2.Ability to use the methods of Speech Recognition and Synthesis
3.Ability to develop the applications about Speech Recognition and Synthesis
4.To be able to gain the skill of interpreting some interrelations among these concepts
5.To be able to use mathematical concepts in solving certain types of problems
Recommended or Required Reading
1.Fundamentals of Speech Recognition, Rabiner and Juang, Prentice-Hall, 1993
2.An Introduction to Text-to-Speech Synthesis, Thierry Dutoit, Kluwer Academic Publishers, Dordrecht Hardbound, ISBN 0-7923-4498-7, 1997
Weekly Detailed Course Contents
Week 1 - Theoretical
Acoustic Theory of Speech Production, Human hearing, acoustics, and phonetics
Week 1 - Preparation Work
Read the related subjects from the Course Books
Week 2 - Theoretical
Signal Representation, Vector Quantization
Week 2 - Preparation Work
Read the related subjects from the Course Books
Week 3 - Theoretical
Speech spectrum analysis (Fourier analysis, cepstral analysis, spectrogram reading)
Week 3 - Preparation Work
Read the related subjects from the Course Books
Week 4 - Theoretical
Fundamental frequency analysis (F0 estimation, prosody models)
Week 4 - Preparation Work
Read the related subjects from the Course Books
Week 5 - Theoretical
Speech synthesis
Week 5 - Preparation Work
Read the related subjects from the Course Books
Week 6 - Theoretical
Linear Prediction (all-pole model, LPC, PARCOR, LSP analysis)
Week 6 - Preparation Work
Read the related subjects from the Course Books
Week 7 - Theoretical
Learning algorithms and application (Viterbi algorithm, Bayes’ Theorem)
Week 7 - Preparation Work
Read the related subjects from the Course Books
Week 8 - Theoretical
Speech coding (waveform coding, PCM, LPC)
Week 8 - Preparation Work
Read the related subjects from the Course Books
Week 9 - Theoretical
Dynamic time warping and acoustic modeling, Midterm exam
Week 9 - Preparation Work
Read all subjects again
Week 10 - Theoretical
Dynamic time warping and acoustic modeling
Week 11 - Theoretical
Hidden Markov Modeling, expectation-maximization, and search
Week 11 - Preparation Work
Read the related subjects from the Course Books
Week 12 - Theoretical
Language Modeling
Week 12 - Preparation Work
Read the related subjects from the Course Books
Week 13 - Theoretical
Graphical Models
Week 13 - Preparation Work
Read the related subjects from the Course Books
Week 14 - Theoretical
Segment-Based ASR, Finite State Transducers
Week 14 - Preparation Work
Read the related subjects from the Course Books
Week 15 - Preparation Work
Read all subjects again
Week 15 - Final Exam
Final exam
Assessment Methods and Criteria
Type of AssessmentCountPercent
Assignment1%5
Term Assignment1%5
Midterm Examination1%20
Final Examination1%70
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140342
Assignment1066
Term Project1066
Individual Work140570
Midterm Examination130232
Final Examination142244
TOTAL WORKLOAD (hours)200
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
PÇ-12
PÇ-13
PÇ-14
PÇ-15
OÇ-1
4
3
4
4
4
4
4
4
4
2
2
OÇ-2
4
5
4
5
4
5
3
4
4
4
3
2
3
OÇ-3
4
5
5
5
5
5
4
4
5
4
4
4
OÇ-4
4
5
5
5
5
5
4
4
5
4
3
3
OÇ-5
4
5
5
4
5
5
4
4
5
4
3
3
4
Adnan Menderes University - Information Package / Course Catalogue
2026