Specialization profile--Audio and Acoustic Signal Processing

The profile Audio and Acoustic Signal Processing focuses on such topics as multimedia data compression, audio/speech processing, distributed signal processing, acoustic signal processing, speech enhancement, sensor localization, pattern recognition and security. The research and coursework cover a broad scope of theory and algorithms in signal processing, information theory and cryptography.

Suggested courses

EE4182	Digital audio and speech processing (not running)		6 EC		details
EE4530	Applied convex optimization		5 EC		details
EE4540	Distributed signal processing (not running)		5 EC		details
EE4560	Information theory (not running)		5 EC		details
EE4685	Machine learning, a Bayesian perspective		5 EC		details
EE4715	Array processing		5 EC		details
ET4386	Estimation and detection		5 EC		details
IN4191	Security and cryptography		5 EC		details

MSc project proposals

Some examples of thesis topics (this list is not exhaustive):

MS3	[New! TUD-NXP] Fusion of mono-static and bi-static radar responses (01.12.2022)
	[New! TUD-NXP] Codesign of 2D Antenna Array and DOA Estimation (01.12.2022)
SPS	Optimizing the analysis of auditory event-related potentials in EEG (with Erasmus Medical Center)
	Machine learning and speech enhancement
	Optimisation and Modelling of speech intelligibility
	Acoustic transfer function estimation for beamforming applications
	ACOUSTIC MODELING OF EARPLUGS
	Adaptive audio processing (with the company Axign)
	Spectral Noise Estimation for Hearing Aids
	Active Noise Reduction for MRIs
	In ear (with hearing aid) based Biomedical Signal Processing
	Audio processing in wireless earbuds (Several assignments with the company Dopple)
	Will High-Mobility Modulations Open Up the Ocean?

Thesis examples

MSP	2014	Evgeni Aizenberg	Computer-Aided Comparative Assessment of Inflammatory Lesions in MRI of the Spine in Axial Spondyloarthritis Patients
		Martijn Gerrits	Evaluation of instrumental measures for the prediction of musical noise in enhanced noisy speech
	2013	Erik Roeling	Improving indoor localization of Android phones: For the use of speech enhancement by using a different calibration signal for each phone and including the relative clock skew
	2012	J.J.M. Van de Sande	Real-time Beamforming and Sound Classification Parameter Generation in Public Environments
SPS	2022	Stephy Annie Curie Rakesh Araya	Predicting noise attenuation level in the earplugs using Gaussian Process Regression
		Yuanyuan Yao	Image-Based Query Search Engine via Deep Learning
		Sebastian Jordan	Distributed Optimisation Using Stochastic PDMM
		Ids van der Werf	Towards Gridless Sound Field Reconstruction
		Mihir Kapadia	Few shot emotion recognition using intelligent voice assistants and wearables
		Tobias Roest	Loudspeakers as recording devices in public address systems
	2021	Niels de Koeijer	Sound Zones with a Cost Function based on Human Hearing
		Ellen Riemens	On the Integration of Acoustics and LiDAR
	2020	Shaoqing Chen	Deep Learning-Based Sound Identification
		Laurens Buijs	Clock skew invariant beamforming
		Giovanni Bologni	Room geometry estimation from stereo recordings using neural networks
	2019	Lantian Kou	Particle Filter based Speaker Tracking in Distributed Pairwise Microphone Networks
		Gabriele Zacca	Inferring the location of reflecting surfaces from acoustic measurements
		Emmaouil (Manolis) Papadakis	Face recognition using traditional machine learning algorithms and deep neural networks with application to face verification
		Husain Kapadia	A Generative Neural Network Model for Speech Enhancement
		Metin Calis	Privacy-preserving consensus averaging
	2018	Konstantios Sachos	On speech enhancement in very low SNRs for smart speakers
		Mert Ergin	Snoring Sound Production and Modelling
		Rik van der Vlist	Phase estimation of recurring patterns in nonstationary signals
		Raissa Lynn	Room Geometry Estimation from Acoustic Echoes
		Costas Kokke	Interferer selection for binaural cue preservation in joint binaural linearly constrained minimum variance beamforming
		Lucas Montesinos	Audio-visual authentication for mobile devices
		Niels van Wijngaarden	Inexact distributed optimization schemes
		Sofia-Eirini Kotti	Clock-Offset Invariant Beamforming in Wireless Acoustic Sensor Networks
		Derk-Jan Hulsinga	The cocktail party problem: GSVD-beamformers for speech in reverberant environments
	2017	Jake Jonkman	Quantized Distributed Optimization Schemes; a monotone operator approach
		Boliang Xu	Packet loss concealment for speech transmissions in real-time wireless applications
		Wangyang Yu	Indoor localization with Low Energy Bluetooth
	2016	Iakov Chalegoua	Investigations into Informed Phase Restoration of Amplitude Spectra for Audio Signals
		Mario Coutino Minguez	Identification of room boundaries for sound field estimation
		Daan Schellekens	Quantization effects in PDMM: A first study for synchronous distributed averaging
	2015	Rodolfo Solera Urcuyo	Speech Based Onset Estimation for Multisensor Localization
		Ingmar Jager	Room Shape Estimation from Acoustic Echoes using Graph-based Echo Labeling
		He Ming Zhang	Distributed Convex Optimization: A Study on the Primal-Dual Method of Multipliers
	2014	Andreas Koutrouvelis	Speech Production Modelling and Analysis
	2007	Christian van Bijleveld	Packet Loss Concealment for Speech Communications

Contact person

For more information about the research group, possible thesis topics, and suggestions for your ISP:

dr.ir. Richard Hendriks

Signal Processing Systems Group

Department of Microelectronics