Master Thesis, 30 HP Denoising and declipping radio audio data
Master Thesis, 30 HP Denoising and declipping radio audio data
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
Are you a student eager to apply your theoretical knowledge and fresh perspectives to real-world challenges At Saab we believe that innovation thrives on new ideas and your master thesis project could be the spark that ignites our next technological breakthrough.
Your role
We recognize the immense value that students bring to our company. Your academic rigor combined with your enthusiasm for cutting-edge technology allows you to approach problems with a unique and insightful lens. At Saab you will have the opportunity to collaborate with experienced engineers and specialists gaining invaluable practical experience while making a tangible contribution to our growth and development.
Background
Radio is a common tool for audio communication during military exercises. High quality audio recordings are important for downstream tasks such as transcription. The audio can however vary substantially in quality due to for instance interference hardware settings or with the quality of the equipment itself. The best solution to avoid quality issues is of course to ensure stable equipment and proper equipment settings however this cannot always be guaranteed and therefore a post hoc solution may be the only available this project the aim is to improve sound quality of already recorded audio.
Description of the master thesis
We are a newly formed team that belongs to the Windows & Apps department which in turn belongs to the Business Area Dynamics. Windows & Apps is mainly focused on developing software used for planning running supervising and evaluating military exercises as well as augmented reality. You can read more about Business Area Dynamics here.
Our teams aim is to via statistical analysis and machine learning extract more value from data collected during military exercises. Data collected may include periodic updates of the soldiers positions various event data such as when a weapon is fired or when a soldier is hit radio audio data and video this project the focus is on the radio audio data.
We have identified two types of issues with the audio data that are available to us; noise in general and clipping. The noise may for instance be due to background sounds Gaussian or harmonic. Clipping means that audio at volumes above some threshold (due to hardware limitations) is set to the value of the threshold. This phenomenon can be viewed as a special form of a missing data problem called censoring. We believe there is potential in attempting to restore the original audio through various statistical and/or machine learning methods that perform denoising and declipping.
Your profile
This master thesis is suitable for a single student. It is not to be done as a group.
You are at the end of your master most likely related to computer science physics engineering or statistics and about to start your master thesis work for 30 HP. The work will be done mainly onsite at SAABs offices in Huskvarna/Jönköping. You are expected to work independently with some supervision from SAAB.
We are looking for someone with the following skills:
Fluency in English
Python
Some common machine learning framework e.g. PyTorch or TensorFlow
An aptitude for problem solving
Solid knowledge in mathematics/statistics
Preferred qualifications:
Fluency in Swedish
Fluency in other European languages
Previous experience with audio analysis
Previous military experience (e.g. conscription service)
We provide the support and guidance you need to translate your theoretical knowledge into practical solutions. Join us and become a driving force behind Saabs technological advancements!
This position requires that you pass a security vetting based on the current regulations around/of security protection. For positions requiring security clearance additional obligations on citizenship may apply.
What you will be a part of
Explore a wealth of possibilities. Take on challenges create smart inventions and grow beyond. This is a place for curious minds brave pioneers and everyone in between. Together we achieve the extraordinary each bringing our unique perspectives. Your part matters.
Saab is a leading defence and security company with an enduring mission to help nations keep their people and society safe. Empowered by its 25500 talented people Saab constantly pushes the boundaries of technology to create a safer and more sustainable world.
Saab designs manufactures and maintains advanced systems in aeronautics weapons command and control sensors and underwater systems. Saab is headquartered in Sweden. It has major operations all over the world and is part of the domestic defence capability of several nations. Read more about us here.
Last application day
Contact information
Caroline Tjäder Svahn Master Thesis Supervisor
Jonathan Andersson Master Thesis Supervisor
Employment Type
Full-Time
