Undergraduate Course: Speech Synthesis (LASC10062)
Course Outline
| School |
School of Philosophy, Psychology and Language Sciences |
College |
College of Humanities and Social Science |
| Course type |
Standard |
Availability |
Available to all students |
| Credit level (Normal year taken) |
SCQF Level 10 (Year 3 Undergraduate) |
Credits |
20 |
| Home subject area |
Language Sciences |
Other subject area |
None |
| Course website |
http://www.ling.ed.ac.uk/teaching/postgrad/modules/ss/ |
|
|
| Course description |
This course explores text-to-speech synthesis by taking a detailed look at the theory and practice of the state of the art speech synthesis systems. Through lectures students will learn the theory of speech synthesis through the lab sessions and assessment students will learn about the practical application of this theory as they design and build their own synthetic voice for a unit selection speech synthesiser. The syllabus include topics such as: approaches to speech synthesis, text selection and recording data for
corpus based approaches, searching inventories for unit selection approaches, prosody, pitch tracking, The Festival speech synthesis system architecture, speech coding for speech synthesis, parameter driven speech synthesis, evaluating speech synthesis and building a unit selection voice.
|
Entry Requirements
| Pre-requisites |
Students MUST have passed:
Speech Processing (Hons) (LASC10061)
|
Co-requisites |
|
| Prohibited Combinations |
|
Other requirements |
None
|
| Additional Costs |
None |
Information for Visiting Students
| Pre-requisites |
Visiting students should have at least 3 Linguistics/Language Sciences courses at grade B or above (or be predicted to obtain this). We will only consider University/College level courses. |
| Prospectus website |
http://www.ed.ac.uk/studying/visiting-exchange/courses |
Course Delivery Information
|
| Delivery period: 2010/11 Semester 2, Available to all students (SV1)
|
WebCT enabled: No |
Quota: None |
| Location |
Activity |
Description |
Weeks |
Monday |
Tuesday |
Wednesday |
Thursday |
Friday |
| Central | Laboratory | | 1-11 | | | | | 15:00 - 15:50 | | Central | Lecture | | 1-11 | | 14:00 - 15:50 | | | |
| First Class |
Week 1, Tuesday, 14:00 - 14:50, Zone: Central. Room 1.17, Dugald Stewart Building |
| Additional information |
Class information:
Tues: Rm 1.17 Dugald Stewart Building
Friday: Lab (rm 3.02) Appleton Tower |
Summary of Intended Learning Outcomes
A student who has attended this course should
Understand the speech synthesis process, and be familiar with the processing steps required to convert text to speech.
Be familiar with the different speech synthesis methods currently used by speech synthesis systems and understand the advantages and disadvantages of each.
Have a detailed understanding of the principles of unit selection speech synthesis, and the issues involved with choosing suitable candidate units to match a given target sequence.
Understand the design issues associated with recording data suitable for building a unit selection voice.
Have the practical experience of having built a synthetic voice themselves.
Be familiar with the different speech coding techniques that can be used for speech synthesis, and understand how these can be used to aid the joining of individual speech segments and how using different signal processing techniques to manipulate speech synthesis output affects the speech quality.
Be in a position to discuss current issues in speech synthesis and see where speech synthesis research is heading in the future.
|
Assessment Information
Exam (50%). One written assignment based on laboratory work (50%)
|
| Please see Visiting Student Prospectus website for Visiting Student Assessment information |
Special Arrangements
| Not entered |
Contacts
| Course organiser |
Dr Simon King
Tel: (0131 6)51 1725
Email: Simon.King@ed.ac.uk |
Course secretary |
Ms Stephanie Fong
Tel:
Email: S.Fong@ed.ac.uk |
|
copyright 2010 The University of Edinburgh -
1 September 2010 6:12 am
|
University Homepage