DSP Machine Learning Intern

ARTURIA; Montbonnot-Saint-Martin; Sur place; EUR 10 000 - 15 000; Plein temps

Résumé du poste

ARTURIA in Grenoble area (Montbonnot-Saint-Martin) offers a 6-month internship in the DSP-Machine Learning team. You will adapt neural network audio models into real-time CPU implementations and embed them in audio plug-ins.

The role targets a PhD student or final-year master with strong DSP and ML skills, Python and PyTorch experience, and good English. Knowledge of C++ and audio DSP is a strong plus, and the project involves research and optimization.

Qualifications

• Strong knowledge in DSP and ML.
• Proficiency in Python and ML frameworks (notably PyTorch).
• Experience with C++ programming and audio DSP is a strong plus.

Responsabilités

• Adapt trained models into efficient CPU real-time implementations.
• Implement the SPTMod architecture in C++ using the Arturia framework.
• Evaluate audio fidelity and real-time viability of modeling.
• Optimize the final C++ implementation.

Connaissances

DSP

Machine Learning

Python

C++

PyTorch

Formation

Master's or PhD student

Outils

PyTorch

C++

Description du poste

Job Description

_Internship description:

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.

Requirements

_Profile:

• 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.

Conditions

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

Location

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