Join the leader in entertainment innovation and help us design the future. At Dolby, science meets art, and high tech means more than computer code. As a member of the Dolby team, you’ll see and hear the results of your work everywhere, from movie theaters to smartphones. We continue to revolutionize how people create, deliver, and enjoy entertainment worldwide. To do that, we need the absolute best talent. We’re big enough to give you all the resources you need, and small enough so you can make a real difference and earn recognition for your work. We offer a collegial culture, challenging projects, and excellent compensation and benefits, not to mention a Flex Work approach that is truly flexible to support where, when, and how you do your best work.

Summary

Recent advancements in audio/visual large language models (LLMs) have demonstrated their potential in various audio/visual comprehension tasks. Prior research has shown the effectiveness of fine-tuning LLMs for both reference-free speech quality assessment, as well as “zero-shot” reference-free speech quality assessment, highlighting applicability of LLMs for quality assessment tasks.

This thesis aims to explore and develop a novel approach for predicting the audio quality of compressed audio using multimodal LLMs. The goal is to predict audio quality on the MUSHRA scale by comparing compressed audio with its uncompressed reference.

Responsibilities:

• Literature Review: Analyze existing methods for audio quality prediction, focusing on the use of multimodal LLMs.
• Model Development: Adapt and fine-tune existing audio/visual LLMs to predict full-reference audio quality, and, if needed, explore intelligent prompt engineering techniques.
• Training and Evaluation: Fine-tune the model using the MUSHRA scale as the target metric. Evaluate the model's performance against established benchmarks and human listening scores.

Requirements:

• Currently pursuing a Master degree in Computer Science, Machine Learning, Statistics, Electrical Engineering, or a related technical field.
• Experience with PyTorch, Python, and NumPy.
• Basic experience in training deep learning models.

Dolby Hiring Entity:
Marienbergstrasse 98, 90411
Nuremberg
Germany