Wednesday: 16:15 - 17:45, weekly (from 19/10/22), Location: W16A 010 Dates on Wednesday, 08.02.2023 14:00 - 15:00, Location: W01 1-117 Detailed knowledge of the theoretical concepts underlying listening tests and of modern designs of listening tests. Knowledge about human auditory perception and its application in e.g. audio quality and digital signal processing.
Subjective listening experiment design and models of human auditory perception will be treated with a focus on application in audio quality assessments (e.g. for sound reproduction) and in digital signal processing algorithm development (e.g. for low bit-rate audio coding and headphone virtualizers).
Understanding the signal processing principles applied to
hearing devices (hearing aids and cochlear implants)
- Amplification and compression
- Speech enhancement and noise reduction
- Signal processing in cochlear implants
- Computational auditory scene analysis
- Automatic classification of the acoustic environment
- Acoustic feedback management
Aktuelle Forschungsarbeiten aus folgenden Gebieten der medizinischen Physik, Signalverarbeitung und Akustik:
Audiologie, Neurosensorik (EEG,MEG, fMRI, OAE,…), Psychoakustik, Sprachakustik, Sprachtechnologie, Signalverarbeitung für Hörgeräte und Multimedia
Goals of the Seminar:
- provide an overview of current mathematical methods used in current machine learning,
- provide knowledge of current computational methods used, such as convolutional networks and deep learning,
- gain practical experience in applying machine learning to standard classification problems,
- program in python using keras and/or pytorch machine learning libraries,
- using GPU-processing for deep network training,
- application to problems from speech and audio signals, and to self-chosen problems.
Structure of the course:
First half (weeks 1 to 7) of the course:
We will provide short lecture segments as an introduction to advanced methods from machine learning
relevant to this course. In particular, this will include convolutional networks and several deep network architectures.
We will also provide an introduction to the relevant programming libraries in python that are used, such as keras and pytorch.
Students will work in a self-paced way on a set of python notebooks that introduce these concepts and that include simple implementation steps.
Second half (weeks 8 to 14) of the course:
Students will work individually or in groups on a self-chosen problem in the setting of a mini-project.
The extent of a mini-project will be limited in size and it will follow the implementation practice learned during the first half of the course.
Project progress, necessary technical steps and possible problems encountered will be addressed at regular meetings.
Examples of projects students worked on during previous courses:
- Music genre classification
- Emotion recognition from speech
- Music melody generation
- Natural language processing for tweets
- introductory course to machine learning, signal processing etc.,
- basic knowledge of python programming,
- (ideally) knowledge of jupyter notebooks,
- (ideally) knowledge of linux.
The participants are actually making a distance from their daily own research thread and implementation towards a wider perspective. They pursue other topics of colleagues and related scientists, which seem to be outside the personal scope or interest, and will yet contribute useful commentary and suggestions. To this, we shall seek literature and pursue intrinsically-motivated study in neighboring and overarching fields of research and education. The results of the study will be grouped systematically and presented in the seminar accordingly. The participants cooperatively work on consensus regarding the scientific merit of publications in terms fundamental relevance or potential utility for own scientific generalization. The themes of the seminar comprise the whole bandwidth of scientific literature on signal processing, machine learning and acoustics with applications in speech technology and hearing aids, for instance, single- and multichannel noise reduction, acoustic sensor networks, digital speech communication, binaural transmission and perception. The graduate participants prove the enhanced perspective obtained by the seminar by enhanced motivation and practice for proposal writing. The undergraduate participants can deliver an oral examination or contribute a formal presentation on a given topic.
The students will learn about recent developments and state-of-the-art approaches in Machine Learning, and their applications to different data domains. By presenting scientific studies in the context of currently used models and their applications, they will learn to understand and communicate recent scientific results. The presentations will use computers and projectors. Programming examples and animations will be used to support the interactive component of the presentations. In scientific discussions of the presented and related work, the students will obtain knowledge about current limitations of Machine Learning approaches both on the theoretical side and on the side of their technical and practical realizations. Presentations of interdisciplinary research will enable the students to carry over their Machine Learning knowledge to address questions in other scientific domains.
In this seminar recent developments of models and algorithms in Machine Learning will be studied. Advances of established modelling approaches and new approaches will be presented and discussed along with the applications of different current algorithms to application domains including: auditory and visual signal enhancements, source separation, auditory and visual object learning and recognition, auditory scene analysis and inpainting. Furthermore, Machine Learning approaches as models for neural data processing will be discussed and related to current questions in Computational Neuroscience.
Vorstellung und Diskussion eigener Forschungspläne, sowie eigener Forschungsergebnisse.
Vorstellung und Diskussion fremder publizierter Forschungsarbeiten.
Schwerpunktthemen sind binaurales Hören, Cochlea Implantate, subkortikale neuronale Verarbeitung, modellbasierte Diagnostik von Hörstörungen, Signalentdeckungstheorie, Psychophysik
Hinweise zum Modul
Related to selected course/s
Related to selected course/s
Skills to be acquired in this module
The aim of this module is, to give students further access to also small courses (3 CP) which address the specific interest of the student and deliver unique in-depth knowledge or the opportunity to train specific engineering skills.