Cumhur Erkut, Dr. Sc. (Tech)

Room: 4.0.02a

Aalborg University

A.C. Meyers Vænge 15

DK-2450 Copenhagen SV, Denmark

Edge AI combined with Active and Perceptual Inference will have a huge transformative potential and impact in the immediate future. My mission is to bridge X-verse and Generative AI through Active and Perceptual Inference and academic/industrial ML / AI engineering practices within the Spatial Web Standard, developed by the Spatial Web Foundation and the IEEE P2874 Spatial Web, Architecture and Governance Working Group. I work towards this mission within the cuer collective through scientific projects.

I have a PhD on acoustics and audio signal processing from Aalto University, Finland, with minor studies on Information Systems (Machine Learning) and general studies on Extended Reality. I have participated in national (Finland, Denmark, and Turkey) and international projects (EU Framework Programs 5-7, and Horizon programs). Between 2007 and 2012, I conducted independent research as an Academy Research Fellow on sonic interaction design (Schema-SID, #120583, Academy of Finland), together with the FP7 IC601 SID project on the same theme. At Aalborg University, I worked on embodied interaction, neural sound and motion synthesis. and AI Engineering.

I am affiliated with the Pioneer Center for AI, served at Danish Data Science Academy as a mentor in 2023, participate to the steering commitee of Movement and Computing (MOCO) and to the program commitee of EAAI Mentored Undergraduate Research Challenge.

news

Mar 20, 2026	🚀 Anders’ PhD work on real-time voice transformation training is selected the EURO-CC DK Use case of the month 7. Cumhur is accepted to the ElevenLabs Professor Impact program.
Dec 11, 2025	🎓 MLME’25 mini-projects are awesome! Students leveraged a wide array of machine learning models to solve diverse media experiences, ranging from interactive gaming and gesture control to complex data analysis and audio recognition. These projects are mostly demonstrated with real-time inference in the following key domains: Interactive Gaming and Simulation Gesture Recognition and Control Systems Audio and Emotion Recognition Computer Vision for Object Detection and Sorting Recommender Systems and Data Analysis I am very proud of the outcomes, congratulate all submitting students, and welcome them to the world of ML/AI inference.
Nov 24, 2025	🥇 x 2 hackathon wins in a week!
Sep 23, 2025	🚀 Publication demo update: The demo videos of real-time speaker and emotion conversion are added to the ISAAR’25 poster.
Sep 19, 2025	🚀 A new COST action, mSPACE (CA24122, 2025-2029). I appreciate the WG1 membership, see more at projects page.

latest posts

selected publications

IEEE

Neural Audio Synthesis for Sound Effects: a Scope Review

Mateo Cámara, Fernando Marcos, Anders R. Bargum, Cumhur Erkut, and 2 more authors

IEEE Transactions on Audio, Speech and Language Processing, 2025

DOI
IWAI

Real-time Active Inference for Auditory Hallucination Modeling in VR-based Voice Conversion

Cumhur Erkut

Proc. Intl. Workshop on Active Inference (IWAI). Presented as a Spotlight, Montreal, Canada , Oct 2025

Website
IEEE

Exploring the Impact of AI-Generated Speech on Avatar Perception and Realism in Virtual Reality Environments

Anders R. Bargum, Emil Sønderskov Hansen, Cumhur Erkut, and Stefania Serafin

In IEEE Conf. Virtual Reality and 3D User Interfaces - Abstracts and Workshops (VRW). Video, audio, and data can be found at the html link , Mar 2025

DOI Supp
Reimagining speech: a scoping review of deep learning-based methods for non-parallel voice conversion

Anders R. Bargum, Stefania Serafin, and Cumhur Erkut

Frontiers in Signal Processing, Mar 2024

Abs DOI arXiv

Research on deep learning-powered voice conversion (VC) in speech-to-speech scenarios are gaining increasing popularity. Although many of the works in the field of voice conversion share a common global pipeline, there is considerable diversity in the underlying structures, methods, and neural sub-blocks used across research efforts. Thus, obtaining a comprehensive understanding of the reasons behind the choice of the different methods included when training voice conversion models can be challenging, and the actual hurdles in the proposed solutions are often unclear. To shed light on these aspects, this paper presents a scoping review that explores the use of deep learning in speech analysis, synthesis, and disentangled speech representation learning within modern voice conversion systems. We screened 628 publications from more than 38 venues between 2017 and 2023, followed by an in-depth review of a final database of 130 eligible studies. Based on the review, we summarise the most frequently used approaches to voice conversion based on deep learning and highlight common pitfalls. We condense the knowledge gathered to identify main challenges, supply solutions grounded in the analysis and provide recommendations for future research directions.