Our Dedication to Advancing MIR Research

We are on a mission...

to revolutionize the world of music through pioneering research in Music Information Retrieval (MIR), focusing on automatic music transcription. Our dedication drives us to push boundaries, exploring uncharted territories to develop extraordinary products. By harnessing cutting-edge technologies, data analysis, and AI, we aim to unlock the intricate secrets of music, transcending limitations and creating tools that inspire musicians, transform industries, and enrich lives. Our commitment to innovation empowers us to shape the future of music, making it more accessible, expressive, and enjoyable for all.

Research Areas

Our primary objective is to foster innovation that has the potential to empower
not just individual musicians but the entire music industry as a whole.

Bachelor and Master's Theses

Our latest student research projects:

We offer Bachelor and Master’s theses in corporation with the Karlsruhe Institute of Technology (KIT) and the Hochschule für Musik Karlsruhe. You are looking for an exciting topic for your thesis, take a look at the IIIIT’s homepage for opportunities.

Recent Publications

Latest news and publications from our research team.

Beat and Downbeat Tracking in Performance MIDI Using an End-to-End Transformer Architecture

22nd Sound and Music Computing Conference (SMC), 2025
Beat tracking in musical performance MIDI is a challenging and important task for notation-level music transcription and rhythmical analysis, yet existing methods primarily focus on audio-based approaches. This paper proposes …

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT

arXiv Preprint, 2025
In this paper, we present a neural network approach for synchronizing audio recordings of human piano performances with their corresponding loosely aligned MIDI files. The task is addressed using …

Fretting-Transformer: Encoder-Decoder Model for MIDI to Tablature Transcription

50th International Computer Music Conference (ICMC), 2025
Music transcription plays a pivotal role in Music Information Retrieval (MIR), particularly for stringed instruments like the guitar, where symbolic music notations such as MIDI lack crucial playability information. This contribution …

Dual Task Monophonic Singing Transcription

Journal of the Audio Engineering Society
Automatic music transcription with note level output is a current task in the field of music information retrieval. In contrast to the piano case with very good results using available large …

A Multimodal Approach to Acoustic Guitar Strumming Action Transcription

Late-Breaking / Demo Session Extended Abstract, ISMIR 2022 Conference
Strumming is a guitar playing technique where instead of playing individual notes, the player strokes over the strings of a chord in an up-or downwards direction. Due to the very short …

Estimation of Music Recording Quality to Predict Automatic Music Transcription Performance

International Conference on SMART MULTIMEDIA (ICSM), 2022
Music signals can nowadays be recorded and further processed by lots of different devices in order to extract additional information like instruments and genre or use parts of those …

Are you interested in joining forces?

Have questions, ideas, or collaborations in mind? We’re here to listen. Reach out to our resesach team for inquiries, partnerships, and more. Your input fuels our innovation.

Let’s shape the future of music together!