Research Associate - Deep Learning for Speech and Audio Coding

at  FraunhoferInstitut fr Integrierte Schaltungen IIS

The Fraunhofer-Gesellschaft (www.fraunhofer.com) currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 30 800 employees work with an annual research budget of 3 billion euros.
Our »Audio and Media Technologies« division at the Fraunhofer Institute for Integrated Circuits IIS in Erlangen constitutes one of the world’s largest organizations dedicated to audio, speech, and media processing. It has been an innovator in sound and vision for over 25 years and repeatedly won international competitions in the field of audio and media, e.g., with MP3 and codecs of the AAC family. More than 200 engineers and scientists develop first-rate technologies that are currently used in over 10 billion devices and have already been licensed to over 1 000 companies worldwide.

• Our speech and audio coding team investigates new ways to solve challenging signal processing challenges using deep neural networks, with a particular focus on speech and audio coding as well as communication applications.
• For this purpose, we explore advanced machine learning techniques such as generative AI (GANs, DDPMs) and evaluate their usefulness for deep neural network learning used in speech and audio coding.
• In this role, you will study and familiarize yourself with new machine learning concepts to represent and synthesize speech as well as audio signals more efficiently.
• Based on your growing insights, you will begin to translate these methods into practical approaches that can be applied in real time on mobile and embedded devices