Best Student Paper Award for Eloi Moliner – Again!
The award-winning paper shows how speech recordings can be improved by removing the room reverberation effect using unsupervised machine learning
Double triumph: Aalto acoustics researchers win big in Italy
The International Conference on Digital Audio Effects (DAFx) 2025 witnessed a remarkable achievement by researchers from the Aalto University Acoustics Lab, as Eloi Moliner and Professor Vesa Välimäki brought home two prestigious paper awards, showcasing cutting-edge innovation in audio signal processing.
Last week, researchers Eloi Moliner and Professor Vesa Välimäki from the Aalto Acoustics Lab were honoured in Ancona, Italy, for their research. The awards were presented at the DAFx 2025 international conference on digital audio effects.
Eloi Moliner, who had earned his Doctor of Science in Technology degree just days before the event, received the Second-Best Paper Award for a collaborative work between him, Prof. Lauri Juvela and Prof. Vesa Välimäki from Aalto University, Mr. Michal Švento and Prof. Pavel Rajmic from Brno University of Technology, and Dr. Alec Wright from The University of Edinburgh. Švento, who collaborated on this study last year when he visited Aalto, presented the paper. The paper explores the use of unsupervised learning to estimate nonlinear audio processing, a breakthrough that could significantly enhance how audio effects are modeled.
Meanwhile, the Third Best Paper Award went to a team led by Prof. Vesa Välimäki, featuring Roope Salmi (Aalto University), Prof. Stefan Bilbao (The University of Edinburgh), Prof. Sebastian Schlecht (University of Erlangen-Nuremberg), and Dr. David Zicarelli, CEO of Cycling '74 (USA). Their paper introduced a novel method for transforming long audio recordings by removing phase information, resulting in a surreal, echoic sound that retains the original timbre while blurring temporal details — a technique with exciting implications for music production and sound design.
This marks Dr. Moliner’s fourth publication award, cementing his reputation as a rising star in the field of audio machine learning and AI.
'It’s a proud moment for the Aalto Acoustics Lab and our collaborators. These awards reflect the strength of our international collaboration and the creativity driving our audio research,' Prof. Välimäki says.
From the links below, you can have a look at the winning articles and listen to the processed sounds:
- Paper on Unsupervised Estimation of Nonlinear Audio Effects (Second Best Paper Award winner)
- Sound examples on Unsupervised Estimation of Nonlinear Audio Effects
- Paper on Zero-Phase Sound via Giant FFT (Third Best Paper Award winner)
- Sound examples on Zero-Phase Sound via Giant FFT
More information
Vesa Välimäki, Professor of audio signal processing
Department of Information and Communication Engineering / Acoustics Lab
School of Electrical Engineering
Aalto University
Best Student Paper Award for Acoustics Lab doctoral student Eloi Moliner
The award-winning paper discusses how to solve inverse problems in audio processing
Aalto Acoustics Lab
Aalto Acoustics Lab is a multidisciplinary research center focusing on audio processing and spatial sound technologies. The laboratory gathers professors and research teams from three different units: Department of Information and Communications Engineering, Department of Computer Science, and Department of Art and Media.
Read more news
Highly sought-after EU funding for three Aalto University researchers
The projects focus on atomically precise materials-engineering, LED-based thermal management and quantum methods in distributed networks.
From sound design to the Cannes red carpet – Working with a filmmaking idol on a Palme d’Or winner
Aalto University alum Pietu Korhonen is responsible for the sound design of the award-winning new film Fjord.
The Foundation for the Advancement of Finnish Securities Markets awards Juho Tuuliainen and Ville Virkkunen for their excellent Master’s thesis in the field of finance
Both students will receive a €3,500 scholarship.