Speech Synthesis I

Uitgebreide vaknaam	Speech Synthesis I
Leerdoelen	Upon the successful completion of the course, the student will have achieved the following learning outcomes: 1. explain the history of speech synthesis and its role in society. 2. explain the components of a text-to-speech system. 3. differentiate between different waveform generation strategies (concatenation and vocoders), and comprehend their advantages and disadvantages. 4. demonstrate how to use HMMs for speech generation. 5. work with established open-source text-to-speech tools such as Festival, WORLD and HTS. 6. create synthetic voices in Festival from recorded data by using knowledge on unit selection. 7. evaluate synthetic speech using human listeners. 8. describe the ethical ramifications of evaluation involving human participants.
Omschrijving	Speech synthesis has come a long way since its beginnings from a niche field with limited interest and high entry requirements. It is now a large field with people of widely varying expertise producing essential components of very successful commercial products. The success of voices like Alexa and Siri build on years of work on speech modelling and parametrization. In this course you will learn the theoretical and practical foundations of speech synthesis. The course is divided into four units. In each you will be given an assignment to complete and at the end of the course you will sit on a written exam that will cover all content.
Uren per week
Toetsvorm	Exam, Project (Course grade = 15% Unit 1 Lab Book + 10% Unit 2 Lab Book + 10% Unit 3 Lab Book + 50% exam)
Vaksoort	master
Docent(en)	V. Verkhodanova, MA.
Entreevoorwaarden	Students are required to have knowledge on programming in Python for voice technology and are able to analyze speech sound systems in the world’s languages by applying phonetic and phonological knowledge.
Opmerkingen
Opgenomen in	Opleiding Jaar Periode Type MSc Voice Technology 1 semester I b verplicht