Postgraduate Course: Speech Processing (LASC11158)
Course Outline
| School | School of Philosophy, Psychology and Language Sciences |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | A foundation course in speech processing for students of linguistics, informatics, and related subjects.
Enrolments for students outwith Philosophy, Psychology and Language Sciences must be approved by the Course Organiser. |
| Course description |
In this course, students investigate the fundamentals of speech signal processing, text-to-speech systems, and automatic speech recognition.
This is a fast-paced course which draws on topics from linguistics, informatics, and engineering, including the following:
Foundations in phonetics and signal processing: sound and waveforms, the connection between speech acoustics and speech articulation, time versus frequency representations of speech, the Discrete Fourier Transform and frequency spectrums, the source-filter model of speech.
Text-to-speech synthesis: components of a concatenative text-to-speech synthesiser, introduction to automatic text analysis, waveform generation and speech modification methods.
Automatic Speech recognition: components of a typical speech recognition system, speech feature representations, measuring similarity in speech using probabilistic methods, Hidden Markov Models (HMMs) for ASR, training and testing probabilistic models with speech data.
The course is delivered as a combination of lectures, an online forum, videos, readings, and practical exercises in the lab. The course work will be based on lab exercises where students investigate an existing text-to-speech system, and build a simple automatic speech recognition system. Students deciding whether to take this course should visit https://speech.zone/courses/speech-processing/ where much of the course material can be found.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | Students MUST NOT also be taking
Speech Processing (LASC11065) AND
Speech Processing (Hons) (LASC10061)
|
Other requirements | The course content involves some mathematical concepts and the course work will involve some coding (e.g. Python and Unix shell scripting). Though we will primarily take a conceptual approach, some background in basic linear algebra and probability will be beneficial, as will some experience in using the Unix command line.
Enrolments for students outwith Philosophy, Psychology and Language Sciences must be approved by the Course Organiser. |
Information for Visiting Students
| Pre-requisites | None |
| High Demand Course? |
Yes |
Course Delivery Information
|
| Academic year 2022/23, Available to all students (SV1)
|
Quota: 60 |
| Course Start |
Semester 1 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 20,
Supervised Practical/Workshop/Studio Hours 30,
Online Activities 60,
Feedback/Feedforward Hours 2,
Summative Assessment Hours 4,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
80 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
40% online quizzes (to be taken through the semester)
30% assignment 1
30% assignment 2
|
| Feedback |
Multiple choice question quizzes will be automatically graded and solutions will be discussed in class and/or on the online forum. Comments will be provided for submitted coursework.
|
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- understand human speech production and perception, including the use of tools for visualising and manipulating speech
- give an overview of the components of automatic speech recognition and speech synthesis systems and describe a simple version of each component
- understand what the difficult problems are in automatic speech recognition and speech synthesis
- perform experiments with speech technology systems and relate theory to practice
- see how knowledge and skills from different areas come together in an interdisciplinary field
|
Reading List
| http://resourcelists.ed.ac.uk/courses/lasc11065sv1sem1.html |
Additional Information
| Graduate Attributes and Skills |
Ability to use standard speech processing packages including Wavesurfer, Praat, Festival and HTK
Basic shell scripting
Scientific writing
Experimental design |
| Keywords | automatic speech recognition,text-to-speech synthesis,speech signal processing,phonetics |
Contacts
| Course organiser | Dr Catherine Lai
Tel: (0131 6)50 2698
Email: |
Course secretary | Mrs Elinor Lange
Tel: (0131 6)51 3188
Email: |
|
|
University Homepage