Postdoctoral Researcher in Text-to-Speech Synthesis (Computer Science) in Zürich

The Media Technology Center (MTC) at ETH Zurich connects research and innovative industry applications to build the media technologies of tomorrow. To achieve this, the center provides a unique arrangement that allows a lively knowledge exchange between industry partners, experts, and students to work on the digital transformation of media, covering salient disciplines such as media technology, digital journalism, and design. To join our interdisciplinary team, we offer a position as a Postdoctoral Researcher in Computer Science.

 

We are looking for a talented candidate to join the MTC as a postdoctoral researcher. The candidate will work on multiple applied research projects (80%), as defined by the center and our media and industry partner, in the areas of Computer Vision, Computer Graphics, Natural Language Processing, Machine Learning, Video- and audio processing. The candidate may also pursue his or her own research (20%) with students at ETH Zurich.

The MTC is  exploring how speech synthesis methods can allow for new possibilities to create engaging audio content. Previously, we have built the first voice assistant that can understand and speak in the local Swiss dialects (low-resource text-to-speech). A new project at MTC aims to expand on this work and explore technologies that allow for controllable, adaptive, and expressive text-to-speech synthesis. While automatic text-to-speech systems have dramatically improved over the past years, current technologies have issues that make them hard to apply for applications in the media industry, especially for radio and video broadcasts. They often lack expressiveness in the produced speech, and the original speaker is often re-identifiable based on the generated speech.

Initially, you will drive the research for our project on expressive text-to-speech synthesis. For this, you will be developing new algorithms and systems, and adapting the state-of-the-art to the specific challenges in the industry. In dialogue with our partners, you will develop novel methods with direct real-world applications. You will be working closely with research engineers who will implement your research into software prototypes. You will supervise 1-3 Bachelor's and Master's students per semester and interns supporting the projects. You will benefit from a lively exchange of interdisciplinary projects at the intersection of machine learning, computer graphics and vision, and natural language processing.

The initial employment contract will be for 12 months. Further contract extensions on an annual basis will be decided during the initial employment.

• Must hold Ph.D. in Computer Science or related fields (e.g., Electrical Engineering, Computational Science)
• Proven track record in speech synthesis or related fields (e.g., publications in venues such as ICASSP, ASRU, ICML, NIPS)
• Interest in working on applied research projects at the intersection between academia and industry.
• Proficiency in written and verbal communication in English.
• Experience in supervising Bachelor and Master students
• Speaking one of the national languages of Switzerland is a plus: German, French, Italian, Romansh.

ETH Zurich is a family-friendly employer with excellent working conditions. You can look forward to an exciting working environment, cultural diversity and attractive offers and benefits.

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our to find out how we ensure a fair and open environment that allows everyone to grow and flourish.