Postdoc in generative modelling of speech and motion

Job description

Human communication involves careful orchestration of speech, gesture and facial expressions. Yet most systems treat these modalities as separate. In the BodyTalk project we take a holistic approach to simultaneous synthesis of human communication for applications in virtual reality, gaming, digital assistants, and social robotics. We build on recent breakthroughs in spontaneous speech synthesis and gesture generation based on deep generative models to train integrated multimodal models on synchronized speech, body motion, and facial data.

We are seeking a postdoctoral researcher with a strong background in probabilistic models, ideally applied to speech or human motion, with a passion to create next generation multimodal generative behaviour models.

You will:

• Develop and evaluate probabilistic models for integrated generation of speech, gesture, and facial expression from text.
• Collaborate in multimodal data collection efforts, curating existing 2D and 3D datasets and leveraging our state-of-the-art performance capture studio.
• Conduct user studies evaluating perceptual quality of generated behaviors.
• Publish in top-tier conferences (e.g., SIGGRAPH, ICMI, IVA, ICASSP) and journals.

What we offer

• A position at a leading technical university that generates knowledge and skills for a sustainable future
• Engaged and ambitious colleagues along with a creative, international and dynamic working environment
• Work in Stockholm, in close proximity to nature
• Guidance on relocating and settling in KTH and in Sweden 
• Collaboration with world-leading researchers in speech and gesture synthesis and multimodal communication, both nationally and internationally
• A supportive and inclusive academic environment with ample possibilities for career development

Read more about what it's like to work at KTH and our benefits.

Qualifications

Requirements

• A doctoral degree or an equivalent foreign degree in speech technology, computer graphics, machine learning, computational linguistics, or a related area. This eligibility requirement must be met no later than the time the employment decision is made.
• Strong experience in deep generative models (e.g., diffusion models, VAEs, transformers)
• Programming proficiency in Python and PyTorch
• Interest in multimodal human communication and virtual agent behavior
• Strong collaborative skills and a track record of publications

Preferred qualifications

• A doctoral degree or an equivalent foreign degree, obtained within the last three years prior to the application deadline
• Experience in speech synthesis, motion generation, motion capture or human-robot interaction is highly meritorious. 
• Awareness of diversity and equal opportunity issues, with specific focus on gender equality

Great emphasis will be placed on personal skills.

Trade union representatives

Contact information to trade union representatives.

To apply for the position

Log into KTH's recruitment system to apply for this position. You are responsible for ensuring that your application is complete according to the instructions in the ad.

Your application should include the following

• CV including relevant professional experience and knowledge.
• Copy of diplomas and grades from university studies (with English or Swedish translation if applicable)
• Brief account of why you want to conduct research, your academic interests and how they relate to your previous studies and future goals. Max one page long.

Your complete application must be received at KTH no later than the last day of application, midnight CET/CEST (Central European Time/Central European Summer Time).

About the employment

The position offered is for, at the most, two years.

A position as a postdoctoral fellow is a time-limited qualified appointment focusing mainly on research, intended as a first career step after a dissertation.

Others

Striving towards gender equality, diversity and equal conditions is both a question of quality for KTH and a given part of our values.

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

It may be the case that a position at KTH is classified as a security-sensitive role in accordance with the Protective Security Act (2018:585). If this applies to the specific position, a security clearance will be conducted for the applicant in accordance with the same law with the applicant's consent. In such cases, a prerequisite for employment is that the applicant is approved following the security clearance.

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.

About KTH

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. Read more here