back to search

Audio Artificial Intelligence for Automotive Systems

ED140030International Experience3 ECTSEnglishWintersemester/SommersemesterLehrstuhl für Akustik mobiler Systeme (Prof. Marburg)
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

What it is about

You learn how AI-supported methods, audio signal processing and acoustic simulation are used specifically for the vehicle interior. By the end you will be able to technically structure in-car audio tasks, prepare and evaluate audio signals, apply suitable ML/DL methods, and professionally assess acoustic simulations and embedded deployments.

What you will be able to do

  • Technically structure in-car audio tasks and derive suitable measurement/data/simulation strategies
  • Explain acoustic peculiarities of the vehicle interior and consider them in tuning, speech processing and simulation
  • Analyze audio signals in the time, frequency and time–frequency domains and prepare them for AI
  • Compute and select audio representations (e.g., spectrograms, Mel-spectrograms, MFCCs, impulse responses, embeddings)
  • Apply ML and DL methods for classification, regression, anomaly detection and Speech-AI tasks
  • Contextualize the basic principles of acoustic simulation (FEM/BEM, geometrical acoustics, Ray Tracing, surrogate models) professionally
  • Quantitatively and auditorily evaluate and validate models and simulation results
  • Consider constraints such as computational effort, latency, small datasets, data privacy, robustness and embedded/edge deployment

What the module consists of

  • VorlesungVermittlung der Theorie zu Audio, akustischer Simulation und Audio‑KI
  • Demonstrationen / HörbeispieleIllustrierende Audio‑Beispiele zur Verknüpfung von Theorie und Praxis
  • Python‑Übungen / NotebooksPraktische Verarbeitung, Feature‑Engineering und reproduzierbare Experimente
  • SimulationsbeispieleAnwendung und Vergleich akustischer Modellierungsverfahren
  • ProjektphaseEntwicklung eines prototypischen Audio‑AI‑ oder Simulationssystems mit Bericht und Präsentation

Teaching method

  • Vorlesungsystematische Einführung in Konzepte und Methoden
  • Audio‑Demonstrationenauditives Verständnis und Evaluation von Verfahren
  • Python‑basierte Übungen / Notebookspraktische Umsetzung, Reproduzierbarkeit und Experimentaufbau
  • SimulationsbeispieleAnwendung von Modellierungsprinzipien ohne proprietäre Vollmodelle
  • Betreute ProjektarbeitTransfer des Gelernten auf realistische Aufgabenstellungen

Dates

LectureAudio Artificial Intelligence for Automotive Systems

From the current semester, not binding.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Reviews are automatically checked before they are published.

Official page in TUMonline · Details are not binding.