hi!
I'm a researcher and musician, particularly focused on computational methods for audio and
music understanding, processing, and identification. You can find some of the things I'm up
to on this website.
Or, here's my CV
Christos Plachouras
background
Education
Queen Mary University of London, Center for Digital Music
(C4DM) - PhD in Artificial Intelligence and Music
Thesis: Multimodal audio language models, Advisors: Emmanouil Benetos,
Johan
Pauwels
Sep 2023 - Present
Universitat Pompeu Fara, Music Technology Group (MTG) -
MSc in Sound and Music Computing
Thesis: Evaluation framework for music representation learning, Advisors: Dmitry Bogdanov, Pablo Alonso
Sep 2021 - Aug 2023
New York University - BSc in Computer
Science, Major in Music, Minor in Sound and Music Computing
Thesis: Hierarchical music structure analysis and similarity, Advisor: Carlos Guedes
Sep 2017 - May 2021
Experience (selected)
Utopia Music - Data Scientist (R&D)
Audio fingerprinting deep learning models for massive-scale broadcast monitoring
Oct 2022 - Jul 2023
Audiostack - R&D Engineer
Programmatic sound design, rearrangement, and mixing
Jan 2022 - Jul 2022
Music and Sound Cultures Research Lab - Research
Assistant
Music similarity, mode recognition, and visualization for large, non-eurogenic music
collections
May 2018 - Jun 2021
NYU Steinhardt - Research Student
Hierarchical music structure analysis and structure similarity
Sep 2019 - May 2019
research
My research is focused on making machines able to understand audio and music. Within that scope, I investigate:
1. how to develop better audio representations
2. how to make better multimodal LLMs, and
3. how to best evaluate multimodal models and ensure their usefulness in real-world applications.
Publications and presentations
(alternatively, see google scholar)
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for
Omni MLLMs |
Li et al.
arXiv, [Under review], 2025
Towards a Unified Representation Evaluation Framework Beyond
Downstream Tasks |
C. Plachouras, J. Guinot, G. Fazekas, E. Quinton, E. Benetos, J. Pauwels
International Joint Conference on Neural Networks (IJCNN), 2025
Learning Music Audio Representations with Limited
Data |
C. Plachouras, E. Benetos, J. Pauwels
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
2025
mir_ref: A Representation Evaluation Framework for Music Information
Retrieval Tasks |
C. Plachouras., P. Alonso-Jiménez, D. Bogdanov
Machine Learning for Audio Workshop, Neural Information Processing Systems (NeurIPS),
2023
Music rearrangement using hierarchical segmentation |
C. Plachouras, M. Miron
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
2023
Utilizing Hierarchical Structure for Audio-Based Music
Similarity |
C. Plachouras
Late-Breaking Demo, International Society of Music Information Retrieval (ISMIR) Conference,
2021
Mapping Timbre Space in Regional Music Collections using HPSS
Decomposition |
K.K. Ganguli, C. Plachouras, S. Sentürk, A. Eisenberg, & C. Guedes
International Conference on Timbre, 2020
Mapping the Sounds of the Swahili coast and the Arab Mashriq |
K. Trochidis, B. Russell, A. J. Eisenberg, K. Ganguli, O. Gonez, C. Plachouras, C. Guedes, & V. DanielsonTROMPA presentation, Digital Libraries for Musicology (ISMIR 2019), 2019
music
Compositions (selected)
Performances (selected)
Rachmaninoff - Piano Concerto No. 2, I. Moderato |
Christos Plachouras, Ioannis Potamousis, Live at NYUAD Blue Hall, December 2018
Bach - Partita No. 2 in C minor, I. Simfonia |
Christos Plachouras, Live at NYUAD Blue Hall, May 2018
Messiaen - Vingt Regards - II. Regard de l'étoile |
Christos Plachouras, Studio Odeon, Athens, October 2016
writing
Perspectives on Music Performance Anxiety |
Why your stage fright uncovers deeper issues in music education and culture
Reflections |
A collection of weekly reflections on topics such as wellbeing, happiness, and meditation.