Doctoral Student in Machine Learning for Synthesis of Speech and Motion

Royal Institute of Technology


Doctoral student in machine learning for synthesis of speech and motion

KTH Royal Institute of Technology


KTH Royal Institute of Technology in Stockholm has grown to become one of Europe’s leading technical and engineering universities, as well as a key centre of intellectual talent and innovation. We are Sweden’s largest technical research and learning institution and home to students, researchers and faculty from around the world. Our research and education covers a wide area including natural sciences and all branches of engineering, as well as architecture, industrial management, urban planning, history and philosophy.


Project description

Third-cycle subject:Computer Science or Speech Technology

At the Division of Speech, Music and Hearing at KTH we create machines that learn to speak, listen, move, and use body language like a human. Our goals are to improve the state-of-the art in machine learning; to understand the behaviour of both humans and machine-learning methods; and to create new science and technology to serve humanity. Do you want to be part of this journey? The area is expanding fast and we need more curious minds to join our research team!

This particular project aims to create new machine learning that addresses real needs in science and applications. Particular focus areas are audio and speech synthesis, and motion synthesis from motion-capture data (e.g., for animation and games). Mathematically, you will primarily work to create and use deep-learning-based probabilistic time-series models. Important concepts are attention and normalising flows (a relative of GANs). Outside machine learning and probability theory the research involves topics from signal processing, NLP, phonetics, and computer graphics.

You will be part of a large and dynamic research group in machine learning for human speech, motion, and behaviour, to which we will add a total of five new PhD students in the coming year. Aptitude for teamwork and interdisciplinary collaboration are therefore important traits.

The position is financed by the national AI initiative WASP, which affords great freedom in choosing one’s research direction, compared to many other PhD projects.

This project sits where mathematics, computer science, and human behaviour meet. If you would like to formulate new, advanced mathematical models that you then can listen to or see them move, and also want to understand why you got the results you got, then this is the place for you!

Supervision: The doctoral student will be placed at the KTH Royal Institute of Technology and supervised by Jonas Beskow.


What we offer

  • The possibility to study in a dynamic and international research environment in collaboration with industries and prominent universities from all over the world.

  • A compulsory individual study plan to support your development in your area of interest.

  • A workplace with many employee benefits and monthly salary according to KTH’s Doctoral student salary agreement.

  • A postgraduate education at an institution that is active and supportive in matters pertaining to working conditions, gender equality and diversity as well as study environment.

  • Work and study in Stockholm, one of Europe’s fastest growing capitals, which is close to both nature and the sea.

  • Help torelocate and be settled in Sweden and at KTH.

  • Expert education in a field in great demand nationally and internationally.



To be admitted to postgraduate education (Chapter 7, 39 § Swedish Higher Education Ordinance), the applicant must have basic eligibility in accordance with either of the following:

  • passed a degree at advanced level,

  • completed course requirements of at least 240 higher education credits, of which at least 60 higher education credits at advanced level, or

  • in any other way acquired within or outside the country acquired essentially equivalent knowledge.



In order to succeed as an doctoral student at KTH you need to be goal oriented and persevering in your work. In the selection of the applicants, the following will be assessed:

  • ability to independently pursue his or hers work,

  • ability to collaborate with others,

  • have a professional approach and

  • analyse and work with complex issues.

Other important traits are a careful and structured approach, and openness toward interdisciplinary research.

Good command of spoken and written English is required. Expertise in machine learning/deep learning and probabilistic modelling, and good programming skills (esp. PyTorch/TensorFlow) are strongly desirable. Experience and interest in areas like speech technology, signal processing, natural language processing (NLP), computer graphics/animation, and perception is also preferred.

After the qualification requirements, great emphasis will be placed on personal qualities and personal suitability.


Target degree: Doctoral degree


Information regarding admission and employment

Only those admitted to postgraduate education may be employed as a doctoral student. The total length of employment may not be longer than what corresponds to full-time doctoral education in four years ' time. An employed doctoral student can, to a limited extent (maximum 20%), perform certain tasks within their role, e.g. training and administration. A new position as a doctoral student is for a maximum of one year, and then the employment may be renewed for a maximum of two years at a time.


Union representatives

You will find contact information for union representatives on KTH's website.

Doctoral section (Students’ union on KTH Royal Institute of Technology)

You will find contact information for doctoral section on the section's website.



Apply for the position and admission through KTH's recruitment system. It is the applicant’s responsibility to ensure that the application is complete in accordance with the instructions in the advertisement.

Applications must be received at the last closing date at midnight, CET/CEST (Central European Time/entral European Summer Time).

Applications must include the following elements:

  • CV including your relevant professional experience and knowledge.

  • Application letter with a brief description of why you want to pursue research studies, about what your academic interests are and how they relate to your previous studies and future goals. (Maximum 2 pages long)

  • Copy of the degree certificate(s) and transcripts of records from your previously attended university-level institutions. Translations into English or Swedish if the original documents are not issued in one of these languages.

  • Representative publications or technical reports. For longer documents, please provide a summary (abstract) and a web link to the full text.


Other information

Gender equality, diversity and zero tolerance against discrimination and harassment are important aspects of KTH's work with quality as well as core values in our organization.

For information about processing of personal data in the recruitment process please read here.

We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.

Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.

Type of employment

Temporary position longer than 6 months

Contract type

Full time

First day of employment

According to the agreement


Monthly salary according to KTH's doctoral student salary agreement

Number of positions


Working hours





Stockholms län



Reference number


Gustav Eje Henter,
Jonas Beskow ,
Anna Olanås Jansson,



Last application date

02.Feb.2020 11:59 PM CET

In your application, please refer to