ºÚÁÏÍø

News

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
Eloi Moliner IWAENC-tapahtumassa.
Eloi Moliner (second from the right) and Jean-Marie Lemercier (right) received the Best Student Paper Award at the IWAENC workshop in Aalborg, Denmark on 12 September, 2024. Photo: Leo McCormack.

Aalto Acoustics Lab's doctoral student Eloi Moliner won the Best Student Paper Award at the International Workshop on Acoustic Signal Enhancement (IWAENC) in Aalborg, Denmark, on Thursday 12 September 2024. The joint first author of the paper was Mr. Jean-Marie Lemercier, a PhD student at the University of Hamburg. The IWAENC workshop, which is held every two years, was attended by around 200 experts in audio and acoustics.

Eloi is a third-year doctoral student at the Aalto School of Electrical Engineering. He studies deep learning and its application to audio enhancement. In this paper, Eloi and his supervisor Professor Vesa Välimäki collaborated with researchers from the University of Hamburg, Germany.

The award-winning paper shows how speech recordings can be improved by removing the room reverberation effect using unsupervised machine learning. The method is based on a diffusion model, which is one of the hot topics in deep learning. This work is an example of explainable AI, as the method provides as an auxiliary result the estimated room response, which it extracts from the speech.

Eloi Moliner also won awards at the 2023 IEEE ICASSP conference last year and at the International Digital Audio Effects Conference DAFX22 two years ago. Eloi plans to defend his doctoral thesis next year.

Congratulations to Eloi and Jean-Marie!

Click to read the article.Many examples of processed speech related to this work are available . 

More information

Vesa Välimäki
Professor of audio signal processing
Department of Information and Communication Engineering / Acoustics Lab
School of Electrical Engineering
Aalto University

Eloi Moliner at the conference.

Best Student Paper Award for Acoustics Lab doctoral student Eloi Moliner

The award-winning paper discusses how to solve inverse problems in audio processing

News
Aalto University Acoustic Lab

Aalto Acoustics Lab

The 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.

  • Updated:
  • Published:
Share
URL copied!

Read more news

An eye by Matti Ahlgren.
Press releases Published:

New macular degeneration treatment the first to halt disease’s progression

Aalto University researchers have uncovered a promising way to treat the dry form of the age- related macular degeneration (AMD) in the early diagnosis phase that could potentially stop its progression. The novel treatment approach aims to strengthen the protective mechanisms of affected cells using heat, explains Professor Ari Koskelainen.
Group of people standing in a line holding certificates. A projector screen is visible behind them.
Awards and Recognition, Cooperation Published:

Aalto Doctoral Education Services Receives Unite! Award

Aalto's Unite! Doctoral Education Team, led by Dr Minna Söderqvist, received an award for their long-term efforts to enhance doctoral mobility and collaboration across the Unite! Alliance. The award ceremony took place during the XII Unite! DIalogue.
Onnitteluruusut_kuva Teemu Ojala
Awards and Recognition Published:

Dean's List scholarships awarded to business students who have excelled in their studies

Dean of the School of Business awards students every autumn
Left: Daniela da Silva Fernandes, right: Robin Welsch.
Press releases Published:

AI use makes us overestimate our cognitive performance

New research warns we shouldn’t blindly trust Large Language Models with logical reasoning –– stopping at one prompt limits ChatGPT’s usefulness more than users realise.