DSP Machine Learning Intern

World Aquatics; France; Hybride; EUR 12 000 - 17 000; Plein temps

Résumé du poste

The internship in the DSP-Machine Learning team within our R&D department at Arturia in Grenoble (Montbonnot-Saint-Martin) offers a 6-month hands-on opportunity to adapt trained PyTorch models for real-time CPU usage and embed them into audio plug-ins.

We seek a PhD student or final-year master/engineering student with solid DSP and ML knowledge, strong Python and PyTorch skills, and an interest in research and English communication. Public transport access is available.

Qualifications

• PhD student or master/final-year engineering student.
• Solid knowledge in DSP and ML.
• Proficiency in Python and ML frameworks (notably PyTorch).

Responsabilités

• Implement the SPTMod architecture in C++ using the Arturia framework.
• Conduct a bibliography on model compression (pruning, knowledge distillation, NAS).
• Apply techniques to concrete cases of effect modeling and compare them.
• Evaluate and optimize audio fidelity and real-time viability of modeling.
• Optimize the final C++ implementation.

Connaissances

DSP

Machine Learning

Python

PyTorch

C++

Audio DSP

Communication

Formation

PhD student, Master student or final-year engineering student

Outils

PyTorch

Python

Arturia framework

C++

Description du poste

Recent research work investigated deep learning methods for modeling audio effects, that is employing neural networks to emulate the behavior of audio hardware.

In particular, a specific architecture was designed and proved to achieve good audio quality on the modeling of dynamic range compressors. The trained models are implemented in Python, with PyTorch, and leverage GPUs to apply a large number of operations per output audio sample. Therefore, these models are not ready to be running in real-time on standard consumer hardware.

Thus, the main objective of this internship is to adapt trained models into more efficient implementations, enabling real-time use on CPUs, and thereby embedding them in audio plug-ins.

Internship objectives

• Implement the SPTMod architecture in C++ using the Arturia framework.
• Conduct a bibliography on model compression, exploring techniques such as pruning, knowledge distillation, and neural architecture search.
• Apply these techniques to concrete cases of effect modeling and compare them.
• Evaluate and optimize both the audio fidelity and the real-time viability of modeling.
• Optimize the final C++ implementation.

Profile required

• Preferably PhD student, or master-level or final-year engineering school student.
• Solid knowledge in Digital Signal Processing (DSP) and Machine Learning (ML).
• Proficiency in Python and previous experience with ML frameworks (notably PyTorch).
• Strong interest in research. Good command of English.
• Experience with C++ programming, audio DSP, good mathematical reasoning and communication skills are a strong plus.

6-month internship in the DSP-Machine Learning team, within our R&D department.

Location: Grenoble (Montbonnot-Saint-Martin), accessible by public transportation.

Does this opportunity sound like a good fit for you?

Company description

Arturia is France’s leading manufacturer of electronic musical instruments. Its mission is to make music creation accessible to everyone.

Arturia began its journey in 1999 with the creation of iconic analog synthesizers in software format, and today enjoys international success thanks to the development of a complete line of synthesizers, MIDI controllers, and audio equipment. Driven by innovation, its products offer a bold, accessible, fun, and inspiring approach to sound exploration.

Arturia continues to grow and currently has more than 190 passionate employees in France, the United States, Hong Kong, Mexico, and the United Kingdom. Arturians share a commitment to excellence, values such as transparency and simplicity, and a culture of celebrating every success.