Curriculum

• Introduction to Voice Technology (5 ECTS):  This course explains the basics of speech synthesis and recognition, gives a brief overview of the history of speech recordings and voice technology, and familiarises students with challenges and pitfalls of the current voice world.  Students not only come in contact with voice technology applications such as voice assistants, smart speakers, and open-source speech recognizers and synthesizers,  but they also get prepared to become responsible and ethical professionals by following GDPR and data ethics lectures. Another important part of this course is the frequent guest lectures by people in the Voice Tech industry and academia that give students the opportunity to discuss and get a glimpse of the voice tech world.

• Programming (5 ECTS):  The main goal of this course is to learn how to code in Python, focusing in voice technology tasks.  Students learn  to create and use voice tech libraries and tools, and come across tasks that are important in building  a new voice-tech system, such as preprocessing, curating and adjusting voice data.  Students also get familiar with  software version management systems and  learn to create code that is reusable and replicable. The course is split evenly into two units, the first providing the essentials of programming  and the second including hands-on work with speech and language data.

• Speech sounds (5 ECTS):  This course provides fundamental knowledge from the fields of phonetics and phonology.  It covers aspects of anatomy and physiology of the vocal tract and ear, discusses how the International Phonetic Alphabet reflects the diversity of speech sounds, and considers applied issues relating to accented speech, speech perception, speech pathologies, and whispered speech, among other topics. In the duration of the course, students develop a Lab Book with their completed speech analysis and processing assignments  that can work as a useful resource, not only for other courses and the thesis project but also for their career in voice technology.

• Machine Learning (5 ECTS):   This course teaches students how to design computational models for specific tasks and problems in a data driven manner. Special attention is given to validation, adaptation and replicability of the models. The coding language of this course is Python and students gain hands-on experience on machine learning and neural network architectures to process tabular data, images, text and, most prominently, sound. These lay the foundation for the speech synthesis and recognition courses.

• Speech Recognition I (5 ECTS):  This course is an introduction to  speech recognition technologies, giving students the opportunity to build their own speech recognizer from scratch and gain a deep understanding of the foundation upon which the state-of-the-art is built. Using this recognizer, students simulate the product development process and make an ASR application that demonstrate in the final week of the course. At the same time,  they are getting prepared for the Speech Recognition II course that takes place in Term 3.

• Speech Synthesis I (5 ECTS):  This courses focuses on the theoretical and practical foundations of speech synthesis.  The students get the opportunity to dive in the history of speech synthesis and its societal impact,  getting familiar with and exploring text-to-speech systems . Another important part of this course is the creation and evaluation of synthetic voice and the ethical ramifications of evaluation involving human participants. 

• Speech Recognition II (5 ECTS): In Speech Recognition II the knowledge for practical speech recognition use cases deepens. In this course students learn about the impact of Deep Neural Networks (DNNs) on the HMM-based framework and get familiar with speech recognition toolkits and interfaces. Moreover, during this course, students build speech recognision systems for under-resourced languages, while invited scholars and professionals present unique  automatic speech recognition applications. In this way students gain an understanding for the impact of speech recognition systems.

• Speech Synthesis II (5 ECTS):  In this course, students learn how deep neural networks can generate speech from text, along with advanced techniques that allow such systems to handle heterogeneous data and to be controllable and applicable in different case scenarios. Students also learn how to work with advanced tools for generating speech and they consolidate knowledge by designing an experiment which answers a research question or showcases a new product.

• Thesis Design (5 ECTS):  This course is dedicated to the design of  the Master’s thesis., focusing on research design and experimental protocol. This is a highly interactive course and includes hands-on training, in-class group exercises, and individual reflection to help students pursue their interests in a rigorous and scientific way. To help streamline their educational experience, students develop 1) a paper based on independent research,  2) a software demonstrator prototype which demonstrates the outcomes of their research,  and 3) a scientific poster related to the paper and demonstrator prototype which is presented in a poster session.  Deliverables (1) and (2) are designed to dovetail with aspects of the master’s thesis and could be integrated into it. Deliverable (3) prepares the students for their thesis defence. To those ends, students also acquire important general skills like project planning, critical analysis, effective communication, and, most importantly, peer review. These skills, alongside their own scientific acumen, are key to students becoming “Masters of Science”.

• Thesis Project (15 ECTS): 

The thesis forms the aptitude test for the MSc Voice Technology. In the course Thesis Design (Term 3) students have already written a research proposal and a related paper with a literature overview, research problem, research questions, appropriate methods for data collection and analysis and a planning for term 4. In this term students elaborate this further, based on the feedback they received from the instructor, and develop it into a thesis. Additionally, students develop further their demonstrator prototype, modifying it from a proof-of-concept to a more polished demonstrator (it is also permitted that a student starts over with a completely new demonstrator in the event that the prototype from the Thesis Design course fell short of their expectations or if the student wants to tackle a different issue for other reasons). This demonstrator should be related to the experiment of the thesis study, or it can also be an application that is built based upon the outcomes of the thesis study.