International Audio Laboratories Erlangen

Theses and Student Jobs

General

  • Please contact Prof. Dr. Nils Peters for possibilities regarding Master Theses, Research Internships, ASC Minor or Major Research Projects, and student jobs.

Specific Offers

1. Deep Metric Learning in Wireless Acoustic Sensor Networks (WASN)

  • Type: Master Thesis
  • Description: Distance measures are important for many applications in WASN. For optimal routing between nodes, acoustical information can provide insights into the spatial relationships between nodes. The psychoacoustical distance between sensed signals helps in fusing and data reduction for optimal transport. The distance between learned manifolds gives distance between audio objects based on embeddings. This thesis evaluate different methods for metric learning. In specific, learning the euclidean distance between embeddings (such as X-vector or E-CAPA) or time signals. The distance function can then be used for speaker localization in WASNs. Research questions are how speaker embeddings perform in comparison to other target-specific representations.
  • Skills: confident in Python programming, some knowledge of distance metrics (e.g. KL divergence, Bregman divergences etc.), knowledgeable either with PyTorch or Tensorflow.
  • References: https://arxiv.org/abs/2206.04763
  • Theory, Development, and Evaluation: 30/30/40
  • Contact: MSc Lorenz Schmidt

2. Realtime source localization implementation for Wireless Acoustic Sensor Networks (WASN)

  • Type: Research Internship
  • Description: This research internship evaluates an optimal placing algorithm for sensor nodes with experiments in source localization. First, the usefulness of the cited positioning algorithm in real-world scenarios is to be evaluated. Second, a real-time implementation should give feedback to the user during source localization. You will get experience implementing real-time source localization and optimal positioning algorithm on hardware. The implemented method can be further developed in context of a master thesis.
  • Skills: Knowledge of Python/Rust for realtime implementation.
  • References: https://arxiv.org/abs/2109.03639
  • Theory, Development, and Evaluation: 5/70/25
  • Contact: MSc Lorenz Schmidt

3. Lightweight Environment Classification for External Sound Handling in Hearables

  • Type: Master Thesis
  • Description: This project is about the development and refinement of a lightweight audio classifier for environmental sound detection in low-power hearables. You will get experience in training, tuning, and model compression using state-of-the-art machine-learning methods. The results of this thesis will inform future developments of hearables at Fraunhofer IIS.
  • Skills: Confident in python programming, knowledgeable in the field of machine learning for audio, and experience working with TensorFlow or PyTorch.
  • References: https://dcase.community/challenge2023/task-low-complexity-acoustic-scene-classification
  • Theory, Development, and Evaluation: 20/40/40
  • Contact: Dr. Michael Lovedee-Turner

Past Offers

Enhancing immersive audio for hearing impaired listeners

  • Status: Filled
    Details
    • Type: Research Internship, Master Thesis
    • Description: Ask for more details
    • Skills: Knowledge of listening tests, auditory models, virtual acoustics. C/C++ programming is a plus
    • Theory, Development, and Evaluation: 20/30/50
    • Contact: Prof. Dr. Nils Peters

Evaluating the effectiveness of debiasing strategies for privacy decision-making in Conversational AI

  • Status: Filled
    Details
    • Type: Research Internship, Master Thesis
    • Description: The task is to evaluate various objective measures to better understand the effect of debiasing strategies and peoples’ underlying thinking processes of privacy decision-making in Conversational AI. Such objective measures include the measurement of reaction or fixation time and pupil dilation. Thereby, the usefulness of these objective measures should be evaluated by designing and implementing a privacy decision-making scenario in CAI and various debiasing strategies and by conducting and analysing a user study using eye-tracking as a preferred method.
    • Theory, Development, and Evaluation: 5/25/70
    • Contact: Anna Leschanowsky, M.Sc.

Prototyping a cloud/edge-based orchestrator for audio-centric, pervasive storytelling

  • Status: Filled
    Details
    • Type: Research Internship, Master Thesis
    • Description: This internship is part of a project that proposes a representation model for adaptive, audio-centric storytelling in pervasive environments enabled by multimedia and IoT devices. Your main goal in the project is the implementation of a proof-of-concept prototype for a cloud/edge-based orchestrator able to interpret model instances and present stories over connected media/IoT devices. This project is in collaboration with Visiting Prof. Marcelo Moreno.
    • Skills: Knowledge on hypermedia, media synchronization and IoT; Python and/or JavaScript programming
    • Contact: Prof. Dr. Nils Peters

Development of a Web-based Interface for Audiovisual Classification Experiments

  • Status: Filled
    Details
    • Type: Research Internship
    • Description: Goal of this internship is to implement a web-based interface for conducting audiovisual classification experiments. The final interface will be used for future listening tests and outreach events.
    • Skills: Web Audio API and html5 programming; Database management; Knowledge in Audio Signal Processing
    • Contact: Prof. Dr. Nils Peters

Evaluation of Voice Anonymization Systems

  • Status: Filled
    Details
    • Type: Research Internship, HiWi
    • Description: In this project you will work with different state-of-the-art voice annonymization algorithms and will compared their performance based on various metrics and speech datasets.
    • Skills: Python programming; Knowledge in Speech Signal Processing and Machine Learning
    • Theory, Development, and Evaluation: 15/35/50
    • Contact: Ünal Ege Gaznepoğlu, M.Sc.

Source Localization in Wireless Acoustic Sensor Networks

  • Status: Filled
    Details
    • Type: Research Internship, ASC Research Project
    • Description: Various source localization algorithms exist for wireless acoustic sensor networks. In this internship, you will study the literature (e.g., this paper) and implement prominent algorithms into an existing signal processing framework. Once the algorithms are implemented, you will evaluate these algorithms under different acoustic conditions and network configurations.
    • Skills: Python programming; Knowledge in Audio Signal Processing, Statistical Signal Processing, and Convex Optimization
    • Contact: Prof. Dr. Nils Peters

Privacy for Voice Assistants

MIMO Room Impulse Response Dataset

  • Status: Filled
    Details
    • Type: Research internship, Student job
    • Description: The goals of this project are:
      • Create a novel dataset of room impulse responses that are measured using a system of distributed loudspeakers and distributed microphones (Multiple-Input and Multiple-Output).
      • Analysis and visualziation of the measured room impulse responses.
    • Skills: Knowledge in room acoustics, Familiarity with acoustic measurement equipment and software, batch scripting in Matlab or Python
    • Contact: Prof. Dr. Nils Peters

Development of a Signal Processing Framework for Distributed Microphone Networks

  • Status: Filled
    Details
    • Type: Research internship, MSc thesis
    • Description: Have you ever wondered how microphones from all your electronic devices can be combined to create a distributed microphone array? During this project you will implement audio processing algorithms for distributed microphone arrays. These algorithms are based on recent literature (e.g., DOI:10.23919/Eusipco47968.2020.9287852) and will contribute to a modular signal processing framefork optimized for distributed microphone arrays.
    • Skills: Experience with software development and DSP implementations (preferably Python or RUST); proficiency in linear algebra and convex optimization
    • Contact: Prof. Dr. Nils Peters

Scene Representation in Wireless Acoustic Sensor Networks

  • Status: Filled
    Details
    • Type: MSc thesis
    • Description: Wireless Acoustic Sensor Networks (WASN) are present everywhere in daily life. Examples (ranging from large to small) are smart cities, home automation, cars or mobile phone ad-hoc networks. Typical applications are hearing aids, hands-free telephony, acoustical monitoring and ambient intelligence. Flexibility is often a key challenge in those topologies and require novel algorithm designed for use-cases where the nodes can (i) join and leave anytime (ii) only communicate with a subset of neighbors. Algorithms working in such scenarios synchronize locally solved problems in a global context. This can be done by splitting variables into local and global variants. Alternating local optimization and global synchronization is at heart of the Alternating Direction Method of Multipliers (ADMM) method. This work applies ADMM to Non-Negative Matrix Factorization (NMF), a parametrized representation of the acoustical scene. NMF represents the spectrogram with a codebook, overlapping codes at specific time with an activation matrix. In WASN the codebook vectors represent the acoustical scene globally, whereas the activations are indicating what is happening at a specific nodes. Once the activations are exchanged, similarity scores can give a clue about the topology and allows reconstruction of the sounds from different clusters. The goal is to derive an algorithm for the NMF variant. The implementation should be compared in terms of adaptivity, convergence and bandwidth requirements to a single node and fusion center.
    • Skills: Audio Signal Processing, Statistical Signal Processing, Convex Optimization
    • Contact: Prof. Dr. Nils Peters

Development and Evaluation of a Rotating Microphone

  • Status: Filled
    Details
    • Type: Research internship, student job, MSc thesis
    • Description: The goals is to develop a microphone apparatus that rotates with a certain velocity on a fixed circular trajectory. The accurate estimation of the instantaneous microphone position is crucial. A functional prototype will be part of future research projects.
    • Skills: Experience and interest in mechanics, electronics, and python software development.
    • Contact: Prof. Dr. Nils Peters

Learnable Acoustical Frontend for Noise Suppression

  • Status: Filled
    Details
    • Type: Research internship, MSc thesis
    • Description: In the area of neural processing for audio signals, very often a fixed acoustical frontend extracts features (e.g., bark-scaled spectrograms, MFCCs, or wavelet coefficients). Replacing such static feature extraction process with trainable equivalents let you gain an insight into their working and can produce interesting results. Your task will be finding fixed parameters which can be updated during training. The goal of your evaluation will be noise suppression. RNNoise flavored architecture gives you a starting point where you can make experiments with the acoustical frontend.
    • Skills: some experience in machine learning, background in noise suppression, some knowledge of wavelets is beneficial
    • Contact: Prof. Dr. Nils Peters

A Study on Affordable Neural Networks

  • Status: Filled
    Details
    • Type: Research internship, MSc thesis
    • Description: In the last decade neural approaches delivered top performing models in many audio fields. Two prominent examples are keyword detection in real environments and scene classification. A main objective for model design is complexity. A more regularized model gives better generalization ability and avoids very complex answers which may turn out to be wrong during testing. The focus of this work are regularization techniques reducing computational complexity as well, making those models more feasible for embedded devices. Already existing techniques are the LassoNet, top-k ReLU, fixed sparsity, matrix factorization, weight quantization and mixture of experts. You will be given two baseline models for keyword detection and scene classification. Together with your supervisor you will develop an overview and make a comparative analysis of mentioned techniques. In a second step the study should compare the trade-off between complexity and performance for selected methods.
    • Skills: experience in machine learning, interest to work with Tensorflow lite/micro or Pytorch Mobile
    • Contact: Prof. Dr. Nils Peters