Postdoc in Personalized AI Voices for Communication Aids Full-time

Postdoc In Personalized Ai Voices For Communication Aids

Millions of people worldwide rely on Speech Generating Devices (SGDs) for communication. These systems provide intelligible speech, but not expressive speech. A terse synthesized message can sound rude when the user meant it neutrally. A joke lands flat. Sarcasm disappears entirely. In the Vetenskapsrådet-funded 4-year project Personalized Voices, we aim to change this. We will do this by giving SGD users not just a voice, but their own voice: one they can shape, control, and rely on to convey what they actually mean. The project develops a speech synthesis architecture with independently controllable dimensions: voice identity (who you sound like), prosodic realization (how you deliver a message), and communicative intent (what emotion or attitude you convey). The research focuses on the design of control mechanisms and evaluation methods that hold regardless of which underlying TTS technology is used. This is a core requirement in a field where generative AI models evolve rapidly.

We are looking for a postdoctoral researcher with a strong background in speech synthesis and machine learning, with an interest in accessibility and human communication.

Your Role

You will:

• Plan and lead recordings of an annotated speech corpus (Swedish and English) with voice actors, covering a broad range of speaking styles, affective states and speech acts.
• Develop and evaluate neural TTS models with multi-dimensional prosody control: voice identity, prosodic realization, and affective state.
• Implement verifier-based feedback in the synthesis loop to ensure generated speech matches the user's intended expression.
• Conduct user studies with SGD users, in collaboration with researcher ant KTH and clinical partners, to evaluate the communicative effectiveness of the developed systems.
• Publish results at leading venues (e.g. Interspeech, ICASSP, SSW) and contribute to open-source release of corpus and models.

Requirements

• A doctoral degree in speech technology, machine learning, computational linguistics, or a closely related field. This eligibility requirement must be met no later than the time the employment decision is made.
• Documented experience with neural speech synthesis models and/or TTS with prosody control.
• Strong programming skills (e.g., Python, PyTorch).
• Ability to work both independently and collaboratively within an interdisciplinary team.
• Good communication skills in English, spoken and written, for day-to-day work

Preferred qualifications

• A doctoral degree or an equivalent foreign degree, obtained within the last three years prior to the application deadline
• Experience with speech corpus collection and annotation.
• Experience with end-user evaluation.
• Awareness of diversity and equal opportunity issues, with specific focus on gender equality

Great emphasis will be placed on personal skills.

KTH shapes the future through education, research and innovation. As a leading international technical university, we play an active role in advancing the transition towards a sustainable society. At KTH, you have the opportunity to grow and develop in a creative and dynamic environment, with good working conditions and attractive benefits. Equality, diversity and equal opportunities are essential to quality and form an integral part of KTH's core values as a university and public authority.

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

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.

The application must include:

• CV including relevant professional experience and knowledge.
• Copy of diplomas and grades from your previous university studies. Translations into English or Swedish if the original documents have not been issued in any of these languages.
• Brief account of why you want to conduct research, your academic interests and how they relate to your previous studies and future goals. Maximally two pages 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).

The position offered is for, at the most, three 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.

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.