Acoustic Scene Classification

Description

Acoustic scene classification has the aim of enabling devices to recognise the acoustic environment. It has been successfully employed in a series of applications, such as intelligent wearable interfaces, context-aware computation, and many more. This topic requires participants to classify acoustic data into several classes of scenes.

 

Task

The student will investigate how to extract spectrograms and train a robust deep learning model to classify the acoustic scenes from a big audio dataset.

 

Utilises

Python

 

Requirements

Deep Learning

 

Languages

English

 

Supervisor

Zhao Ren (zhao.ren@informatik.uni-augsburg.de)

Correlation Between Emotion and Deception

Description

Is deception emotional?

 

Task

An in-depth analysis of the correlation between emotion and deception

 

Utilises

-

 

Requirements

Basic programming knowledge

 

Languages

English

 

Supervisor

Shahin Amiriparian, M. Sc. (shahin.amiriparian@informatik.uni-augsburg.de)

Audio-Based Depression Recognition App

Description

Depression recognition

 

Task

Develop an Android application using available machine learning models for depression recognition

 

Utilises

Android Neural Networks API (NNAPI)

 

Requirements

Basic programming knowledge

 

Languages

German, English

 

Supervisor

Shahin Amiriparian, M. Sc. (shahin.amiriparian@informatik.uni-augsburg.de)

Soundscape Emotion Recognition

Description

Our daily lives are surrounded by chaotic noise, methods to alter our sonic enviroments are needed urgently. Computational generation approaches for audio are becoming more robust, and offer the chance for emotion-based conditioning of high fidelty audio. 

 

Task

The student will be provided with tools to investigate methods to extract meaningful features from soundscapes, as awell generate novel emotonally conditioned ones. 

 

Utilises

Python 

 

Requirements

Deep learning

 

Languages

English

 

Supervisor

Alice Baird (alice.baird@informatik.uni-augsburg.de)