Internship - Deep learning-based enhancement of parametric stereo audio compression
Eindhoven - HTC 34, Netherlands
Philips
Lue lisää Philipsistä ja katso miten terveydenhuollon-, kulutuselektroniikka- ja valaistus-divisiooniemme innovaatiot auttavat parantamaan ihmisten elämää.Job Title
Internship - Deep learning-based enhancement of parametric stereo audio compressionJob Description
Project Title: Deep learning-based enhancement of parametric stereo audio compression
Project Duration: 6 months
Background: In parametric stereo coding, a stereo audio signal is downmixed to a mono signal, and stereo parameters are estimated and transmitted to the decoder. At the decoder, the stereo signal is reconstructed using the mono downmix and the transmitted stereo parameters. While performance has been promising, further improvements and evaluations are necessary.
Project Summary: This non-thesis project aims to advance our current work on neural network-based parametric stereo coding. The objective is to improve the quality of the decoded signal while maintaining coding efficiency relative to the baseline signal processing based parametric stereo coder.
Key Tasks and Deliverables:
- Literature Review and Familiarization
- System Performance Verification
- Quantizer Integration and Evaluation
- Latent variable size analysis
- Exploration of Alternate Architectures
- Final Report and Presentation
Required Skills:
- Master’s student in the field of Electrical Engineering\ Computer Engineering with good understanding and enthusiasm for learning about neural networks and deep learning frameworks.
- Proficiency in Python and relevant libraries (PyTorch, Torchaudio).
- Familiarity with audio signal processing/coding concepts (e.g., down/up-mixing, quantization).
- Analytical skills to evaluate different neural network architectures.
Supervision and Support: The student will have access to the necessary computational resources and audio datasets required for the project. Regular meetings will be held to discuss progress, address challenges, and refine approaches.
Project Assessment: The student’s performance will be assessed based on regular progress reports, the final report, the quality of the proposed solutions, and the effectiveness of the implemented modifications.
How we work together
We believe that we are better together than apart. For our office-based teams, this means working in-person at least 3 days per week.
Onsite roles require full-time presence in the company’s facilities.
About Philips
We are a health technology company. We built our entire company around the belief that every human matters, and we won't stop until everybody everywhere has access to the quality healthcare that we all deserve. Do the work of your life to help the lives of others.
• Learn more about our business.
• Discover our rich and exciting history.
• Learn more about our purpose.
If you’re interested in this role and have many, but not all, of the experiences needed, we encourage you to apply. You may still be the right candidate for this or other opportunities at Philips. Learn more about our culture of impact with care here.
Our intern remuneration package:
- Monthly full-time allowance between €500 - €700 gross, depending on educational level and if you would need to relocate to The Netherlands. If you will perform a part-time internship you will receive the allowance pro-rata.
- Housing compensation, in case of relocating to the vicinity of the office, €300,- net if location is in the vicinity of Amsterdam, €255,- net for all other Philips locations. You need to provide a rental contract of the land lord, and your normal home-work travel distance need to be more than 50 km or travel time (one way trip) need to be more than 1.5 hours.
- Travel compensation, if you are not eligible for a free public transport card; you will receive max. €192,- net depending on the distance between your home address and the Philips location.
- Paid holidays per internship term.
- The opportunity to buy Philips equipment at our Philips shop
Please note that to be considered for an internship, you need to be registered as a student during the entire internship period. Formal documentation of which may be requested at any time. Please note that the contents of our regular internship assignments are not suitable for professionals (and/or MBA students) with professional work experience
#LI-Field & #LI-Office
Tags: Architecture Deep Learning Engineering Python PyTorch
More jobs like this
Explore more career opportunities
Find even more open roles below ordered by popularity of job title or skills/products/technologies used.