| School/Faculty/Institute | Faculty of Engineering | ||||||
| Course Code | EE 476 | ||||||
| Course Title in English | Introduction to Speech and Language Processing | ||||||
| Course Title in Turkish | Konuşma ve Dil İşlemeye Giriş | ||||||
| Language of Instruction | EN | ||||||
| Type of Course | Seçiniz | ||||||
| Level of Course | Seçiniz | ||||||
| Semester | Spring | ||||||
| Contact Hours per Week |
|
||||||
| Estimated Student Workload | 149 hours per semester | ||||||
| Number of Credits | 6 ECTS | ||||||
| Grading Mode | Standard Letter Grade | ||||||
| Pre-requisites |
EE 204 - Signals and Systems |
||||||
| Co-requisites | None | ||||||
| Expected Prior Knowledge | Prior knowledge in discrete-time Fourier Transform, basics of probability and statistics is expected. | ||||||
| Registration Restrictions | Only Undergraduate Students | ||||||
| Overall Educational Objective | To learn the fundamentals of speech and language processing, and real-world speech and language processing applications. | ||||||
| Course Description | This course provides an introduction to speech and language processing with a focus on real-world applications such as automatic speech recognition, spelling correction, information retrieval and text-to-speech. The following topics are covered: signal processing for speech, Hidden Markov Models, acoustic and language modeling, and basic building blocks of real world speech and language processing applications. |
Course Learning Outcomes and CompetencesUpon successful completion of the course, the learner is expected to be able to:1) Understand the basic mechanisms of speech production and perception; 2) Analyze the speech signal using its time domain and frequency domain representations, and other representations in which it can be modeled; 3) Understand the fundamental methods and models used in language processing; 4) Use algorithms to built speech and language processing systems; 5) Describe some applications of statistical techniques used in (real-word) speech and language processing systems; 6) Prepare a well-organized written report and presentation for a speech and language processing application implementation; 7) Demonstrate team effort during the implementation of speech and language processing application. |
| Program Learning Outcomes/Course Learning Outcomes | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
|---|
| N None | S Supportive | H Highly Related |
| Program Outcomes and Competences | Level | Assessed by |
| Prepared by and Date | EBRU ARISOY SARAÇLAR , January 2020 |
| Course Coordinator | MEHMET FEVZİ ÜNAL |
| Semester | Spring |
| Name of Instructor |
| Week | Subject |
| 1) | Introduction to Speech and Language Processing |
| 2) | Fundamentals: Sound and Human Speech Production -- Acoustical Model of Speech Production |
| 3) | Fundamentals: Hearing and Speech Perception |
| 4) | Speech Signal Representations |
| 5) | Speech Signal Representations |
| 6) | Speech Signal Representations |
| 7) | Algorithms for Estimating Speech Parameters |
| 8) | Regular Expressions, Text Normalization, Edit Distance |
| 9) | Language Modeling with N-grams |
| 10) | Vector Semantics |
| 11) | Hidden Markov Models |
| 12) | Hidden Markov Models |
| 13) | Speech and Language Processing Applications: Speech-to-Text (Speech Recognition) |
| 14) | Speech and Language Processing Applications: Spelling Correction & Noisy Channel |
| 15) | Final Exam/Project/Presentation Period |
| 16) | Final Exam/Project/Presentation Period |
| Required/Recommended Readings | Text books: 1) Rabiner and Schafer, Theory and Applications of Digital Speech Processing, Pearson Prentice Hall, 2011. 2) Jurafsky and Martin, Speech and Language Processing, 2nd edition. (See https://web.stanford.edu/~jurafsky/slp3/ for 3rd edition draft) Reference Text Books: Benesty, Sondhi, and Huang (Eds.), Springer Handbook of Speech Processing, Springer. Deller, Proakis, and Hansen, Discrete Time Processing of Speech Signals,IEEE Press. Huang, Acero and Hon, Spoken Language Processing, Prentice Hall. [HAH] Quatieri, Discrete-Time Speech Signal Processing, Prentice Hall. [Q] Rabiner and Juang, Fundamentals of Speech Recognition, Prentice Hall. [RJ] Rabiner and Schafer, Digital Processing of Speech Signals, Prentice Hall. | |||||||||||||||
| Teaching Methods | Lectures/contact hours using “flipped classroom” as an active learning technique | |||||||||||||||
| Homework and Projects | There will be 4-5 homework assignments and a final project. | |||||||||||||||
| Laboratory Work | None | |||||||||||||||
| Computer Use | Students will use software in some of their assignments and project. | |||||||||||||||
| Other Activities | None | |||||||||||||||
| Assessment Methods |
|
|||||||||||||||
| Course Administration |
saraclare@mef.edu.tr (0212) 3953677 Instructor’s office and phone number: 5th Floor, (0212) 3953677 office hours: TBA email address: saraclare@mef.edu.tr Rules for attendance: - Missing a midterm: Provided that proper documents of excuse are presented, a make-up exam will be given for each missed midterm. Missing a final: Faculty regulations. A reminder of proper classroom behavior, code of student conduct: YÖK Regulations Academic Dishonesty and Plagiarism: YÖK Regulations |
|||||||||||||||
| Activity | No/Weeks | Hours | Calculation | ||||
| No/Weeks per Semester | Preparing for the Activity | Spent in the Activity Itself | Completing the Activity Requirements | ||||
| Course Hours | 14 | 1 | 3 | 56 | |||
| Project | 1 | 29 | 2 | 31 | |||
| Homework Assignments | 5 | 4 | 4 | 40 | |||
| Midterm(s) | 2 | 10 | 1.5 | 23 | |||
| Total Workload | 150 | ||||||
| Total Workload/25 | 6.0 | ||||||
| ECTS | 6 | ||||||