Master Thesis Features Exploitation of Acoustic Signals Using Wavelet Networks

Bosch Group; Renningen; Vor Ort; EUR 40.000 - 60.000; Vollzeit

Zusammenfassung

Una entreprise de technologie de renommée mondiale recherche un stagiaire pour une thèse de master sur le traitement des signaux acoustiques. Vous explorerez des méthodes innovantes en utilisant des réseaux de neurones pour analyser des scènes acoustiques, tout en tenant compte de la conception matérielle. Ce stage est adapté aux étudiants en Master en ingénierie électrique ou informatique et offre une occasion d'appliquer vos compétences dans un environnement dynamique.

Qualifikationen

• Master en Ingénierie Électrique, Informatique ou équivalent requis.
• Expérience en conception numérique et réseaux de neurones est nécessaire.
• Individu autonome avec une approche structurée souhaitée.

Aufgaben

• Explorer diverses approches pour représenter des signaux acoustiques pour les réseaux de neurones.
• Enquêter sur diverses méthodes de représentation des données d'entrée et topologies de réseau.
• Prendre en compte la conception matérielle pour assurer la faisabilité des implémentations.

Kenntnisse

Digital Design

Python

Neural Networks

Ausbildung

Master studies in Electrical Engineering

Master studies in Computer Science

Tools

(System)Verilog/VHDL

Jobbeschreibung

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people's lives. Our promise to our associates is rock-solid: we grow together, enjoy our work, and inspire each other. Join us and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Prior to feeding data to neural networks, the spectrum is typically generated using sliding windows FFT and MFCC on acoustic signals. This approach treats the acoustic signal as an image, allowing image-based neural networks, such as CNNs, to perform various tasks, including keyword spotting. However, extracting temporal and frequency information from the spectrum requires heavy pre-processing, and CNN-based neural networks may be ineffective for such tasks.

During your Master thesis, you will explore various approaches to leverage features present in acoustic signals. By utilizing time-encoding neural networks, the time series characteristics of acoustic signals can be better represented without extensive pre-processing.

You will investigate various input data representation methods and network topologies, such as wavelet networks, to analyze acoustic scenes, enabling direct processing of input into neural networks.

Additionally, hardware design considerations will be a key factor in designing processing chains, including neural network design, to ensure hardware implementation feasibility.

Qualifications

• Education: Master studies in Electrical Engineering, Computer Science, or comparable
• Experience and Knowledge: experience in Digital Design, (System)Verilog/VHDL, Python; background in Neural Networks
• Personality and Working Practice: independent individual with a structured approach to work
• Enthusiasm: keen interest in future technologies and trends; passion for innovation
• Languages: fluent in English, German is a plus

Additional Information

Start: according to prior agreement

Duration: 6 months

Requirement for this thesis is enrollment at university. Please attach your CV, transcript of records, examination regulations, and if applicable, a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. We welcome all applications, regardless of gender, age, disability, religion, ethnic origin, or sexual identity.

Need further information about the job?
Andre Guntoro (Functional Department)
[phone]

#LI-DNI