KEYWORD |
Audio Synthetic Data for Machine Learning
Tesi esterna in azienda
Parole chiave AUDIO, MACHINE LEARNING, MACHINE LEARNING, ARTIFICIAL NEURAL NETWORKS, SYNTHETIC DATA
Riferimenti FABRIZIO RIENTE
Gruppi di ricerca VLSILAB (VLSI theory, design and applications)
Descrizione Innovative time-frequency analysis and processing functions for isolating and modifying sound components can be used to assessing the influence of sounds on human perception. The Thesis goal is the creation of a virtual environments to analyze and optimize the vehicle in-vehicle sound reproduction and to create a synthetic dataset to train new Machine Learning models to recognize sounds.
Conoscenze richieste Python
Scadenza validita proposta 03/04/2025
PROPONI LA TUA CANDIDATURA