I am a senior scientist at Fraunhofer IDMT with a focus on applied research in music information retrieval & machine listening and I’m currently working on my habilitation at the TU Ilmenau.
In my research, I combine techniques from machine learning / deep learning and audio signal processing. On the “ambient sound” side, I work mostly on sound event detection, sound polyphony estimation, and acoustic scene classification and possible applications for urban sound monitoring and bioacoustic research. One the “music” side, I’m mostly interested in automatic music transcription and instrument recognition.
Besides my research, I have a big passion for playing & teaching music (bass guitar & percussion).
Current Projects
-
KI-gestützte Audioanalyse von Musik und Soundscapes - Bi-weekly seminar at the HfM Weimar, which will be held jointly with Prof. Martin Pfleiderer over the winter semester 2022/23.
- Machine Listening for Music and Sound Analysis - 6-part lecture on audio signal processing & deep learning applied for music information retrieval (MIR) and environmental sound analysis (ESA)
- The lecture will be held for the third time this winter semester at the TU Ilmenau Lecture Page and will be continuously extended in the upcoming years.
- Groovecell - Online Learning for Bass and Drums
- LMNT7 - Progressive Rock
News
-
22.09.2022: I’m happy to co-organize a structured session entitled Sound Analysis for Music and Audio Signals (Details) at the upcoming DAGA 2023 together with Prof. Meinard Müller and Prof. Sebastian Stober
-
20.07.2022: I’m honored to be invited to be part of the editorial board of the EURASIP Journal on Audio, Speech, and Music Processing
-
14.07.2022: Our ISMIR paper “Multi-pitch Estimation meets Microphone Mismatch: Applicability of Domain Adaptation” (co-authored with Franca Bittner, Marcel Gonzales, Maike Richter, and Hanna Lukashevich) was accepted!
-
19.05.2022: I gave a talk at the AES Europe Spring Convention on Classifying Sounds in Polyphonic Urban Sound Scenes, where I introduced the Urban Sound Monitoring (USM) dataset
-
27.04.2022: I gave a presentation entitled “Erkennung akustischer Quellen in komplexen Szenarien” (in German) at the 17. Jenaer Akustik-Tag.
-
Published a novel version of the Urban Sound Monitoring (USM) dataset for sound event tagging in polyphonic soundscapes.
-
Small dataset published for piano multipitch estimation evaluation: PIANO-AUG - Piano Multipitch Estimation with Augmentation Dataset
-
Paper accepted for the AES Europe Spring 2022 (AES’s 152nd convention): “Classifying Sounds in Polyphonic Urban Sound Scenes”
-
Abstract accepted at the DMRN+16 Digital Music Research Network One-day Workshop 2021: A Benchmark Dataset to Study Microphone Mismatch Conditions for Piano Multipitch Estimation on Mobile Devices (collaboration with Franca Bittner, Maike Richter, Marcel Gonzalez, and Hanna Lukashevich)
-
Best paper award at the CMMR 2021 for our paper “Deep Learning-Based Music Instrument Recognition: Exploring Learned Feature Representations” (Michael Taenzer, Stylianos I. Mimilakis and Jakob Abeßer): Twitter announcement
-
Two abstracts submitted to DAGA 2022: Analyzing Bird and Bat Activity in Agricultural Environments using AI-driven Audio Monitoring (collaboration with Prof. Christoph Scherber, Dr. Svenja Bänsch, Xiaoyi Wang, and Hanna Lukashevich) and Construction-sAIt: Multi-modal AI-driven technologies for construction site monitoring (collaboration with Dr. Alexander Loos and Prachi Sharma)
-
New pre-print published: Towards Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning (collaboration with Prof. Meinard Müller)
-
I’m a guest editor for the EURASIP Journal on Audio, Speech, and Music Processing (JASM) call: Recent advances in computational sound scene analysis (together with Emmanouil Benetos, Annamaria Mesaros, Wenwu Wang)