Masterarbeiten – Angeboten
Deep Learning Methods for Bearing Fault Detection
Proposal for a Master Thesis Topic: Deep Learning Methods for Bearing Fault Detection Description: The measurable vibrations of machines during operation contain much information about the machine's condition. During normal operation a machine exhibits a characteristic vibration signat...
Zeitlich-Örtliche Prädiktion für eine effizientere Videocodierung
Vorschlag für eine Masterarbeit / Forschungspraktikum Thema: Zeitlich-Örtliche Prädiktion für eine effizientere Videocodierung Beschreibung: Aufgrund der hohen anfallenden Datenmenge bei Videos ist es wichtig, diese verlustbehaftet zu komprimieren. Nur so wird es möglich Filme auf Datenträgern z...
Underdetermined Source Separation by Combination of Directivity Gain
Proposal for a Master Thesis Topic: Underdetermined Source Separation by Combination of Directivity Gain Description: Acoustic mixtures are ubiquitous in signal processing, and recovering the constituent signal components is often highly desirable. Besides the typically convolutive demixing mode...
Source Localization using Manifold Learning
Proposal for a Master Thesis Topic: Source Localization using Manifold Learning Description: Acoustic source localization is a precondition for many subsequent signal processing algorithms. It can be accomplished by mapping one or more acoustic features via an analytical mathematical model or a ...
Learning Data-Dependent Transformations for Ego-Noise Suppression
Proposal for a Master Thesis Topic: Learning Data-Dependent Transformations for Ego-Noise Suppression Description: Robot audition describes the research area of human-robot interaction by speech. Therefore, robots are often equipped with microphone arrays to capture their surrounding acoustic sc...
Fast Multichannel Nonnegative Matrix Factorization (MNMF) for Ego-noise Suppression
Proposal for a Master Thesis Topic: Fast Multichannel Nonnegative Matrix Factorization (MNMF) for Ego-noise Suppression Description: Ego-noise, i.e., the mechanical noise of robots, is a severe problem in robot audition since it corrupts recordings and therefore degrades performance of, e.g., a ...
Exploring Attention Models for Speech Enhancement
Proposal for a Master Thesis Topic: Exploring Attention Models for Speech Enhancement Description: In the field of machine learning, recurrent neural networks (RNNs) using long short-term memory (LSTM) have achieved impressive results in natural language processing, text prediction, speech enha...
Evaluation of the Spatial Distribution of Ego-Noise employing Multichannel Non-Negative Matrix Factorization
Proposal for a Master Thesis Topic: Evaluation of the Spatial Distribution of Ego-Noise employing Multichannel Non-Negative Matrix Factorization Description: Mobile robots generate significant self-induced noise, e.g., by its mechanical joints and motors, which is referred to as ego-noise. Its s...
Dereverberation with the Weighted Prediction Error Method
Proposal for a Master Thesis Topic: Dereverberation with the Weighted Prediction Error Method Description: A speech signal recorded in a room will inevitably be affected by reverberant components produced by the reflections of sound waves on walls or objects in the acoustic environment. Reverber...
Double-Talk Detection for Robot Audition
Proposal for a Master Thesis Topic: Double-Talk Detection for Robot Audition Description: In an Acoustic Echo Cancellation (AEC) problem, the performance of an acoustic echo canceler is usually impaired by the presence of a near-end interferer. This double-talk situation is often addressed using...
Deep Learning Based Anomaly Detection for Industrial Applications
Proposal for a Master Thesis Topic: Deep Learning Based Anomaly Detection for Industrial Applications Description: One of the important tasks in industrial applications is visual inspection. Till date, a lot of the visual inspections are carried out manually. It is desired to automate these insp...
Coherence-based Multichannel Double-talk Detection
Proposal for a Master Thesis Topic: Coherence-based Multichannel Double-talk Detection Description: In a multichannel acoustic echo cancellation scenario, an active near-end speaker poses a serious challenge to the identification of the acoustic echo paths between loudspeaker and microphones, as...
Blind Blind Sampling Rate Offset Estimation for Wireless Acoustic Sensor Networks through Coherence Drift Estimation
Proposal for a Master Thesis Topic: Blind Blind Sampling Rate Offset Estimation for Wireless Acoustic Sensor Networks through Coherence Drift Estimation Description: In Wireless Acoustic Sensor Networks (WASNs) spatially distributed nodes allow for multi-channel array signal processing tasks, e....
Analyse und Steuerung von Adaptiven Mikrofonarrays
Proposal for a Master Thesis Topic: Analyse und Steuerung von Adaptiven Mikrofonarrays Description: Robot audition describes the research area that aims at providing humanoid robots with ’technical ears’ to allow, e.g., reaction to acoustic events and speech communication with humans. For this, ...
Adaptive Speech Dereverberation based on Linear Prediction
Proposal for a Master Thesis Topic: Adaptive Speech Dereverberation based on Linear Prediction Description: A speech signal recorded in a room will inevitably be affected by reverberant components produced by the reflections of sound waves on walls or objects in the acoustic environment. Reverbe...
Acoustic Source Tracking using Manifold Learning
Proposal for a Master Thesis Topic: Acoustic Source Tracking using Manifold Learning Description: The aim of acoustic source localization is to estimate the position of one or several sound sources from observed microphone signals. For moving sources usually a tracking algorithm is appended, whi...
Acoustic Scene Analysis with Manifold Learning
Proposal for a Master Thesis Topic: Acoustic Scene Analysis with Manifold Learning Description: The knowledge of physical parameters describing the acoustics of a room is highly relevant for a multitude of applications, e.g., automatic speech recognition. The reverberation time T60 is one of the...
A probabilistic approach to image resampling
Proposal for a Master Thesis Topic: A probabilistic approach to image resampling Description: Image processing often produces pixels that are not located on integer pixel positions. If an image is e.g. rotated, the pixels are located on non-integer positions after the rotation. We refer to thes...
A Denoising Autoencoder for Speech Enhancement
Proposal for a Master Thesis Topic: A Denoising Autoencoder for Speech Enhancement Description: Speech Enhancement describes the attempt to remove noise and interfering speakers from speech recordings. Even though many algorithms have been proposed to approach this challenge, it is far from bein...
Videocodierung für neunronale Detektionsnetzwerke
Vorschlag für eine Masterarbeit / Bachelorarbeit / Forschungspraktikum / Projektarbeit Thema: Videocodierung für neunronale Detektionsnetzwerke Beschreibung: Üblicherweise sind aktuelle Videocodecs auf den Menschen als finalen Beobachter des komprimierten Videos ausgelegt und optimiert. Allerdin...