Dorien Herremans Explained

Dorien Herremans
Birth Date:	26 July 1982
Birth Place:	Belgium
Occupation:	Associate Professor, Singapore University of Technology and Design

Dorien Herremans is a Belgian computer music researcher. Herremans is a tenured associate professor in the Singapore University of Technology and Design,^[1] and previously held a joint appointment at the Institute of High Performance Computing, A*STAR. She also works as a certified instructor for the NVIDIA Deep Learning Institute and is director of SUTD Game Lab.^[2] Before going to SUTD, she was a recipient of the Marie Sklodowska-Curie Postdoctoral Fellowship at the Centre for Digital Music (C4DM) at Queen Mary University of London, where she worked on the project MorpheuS: Hybrid Machine Learning – Optimization techniques To Generate Structured Music Through Morphing And Fusion.^[3] She received her Ph.D. in Applied Economics on the topic of Computer Generation and Classification of Music through Operations Research Methods. She graduated as a commercial engineer in management information systems at the University of Antwerp in 2005. After that, she worked as a Drupal consultant and was an IT lecturer at the Les Roches University in Bluche, Switzerland. She also worked as a 'mandaatassistent' at the University of Antwerp, in the domain of operations management, supply chain management and operations research.

Herremans' work focuses on generative music AI, data mining for music classification (hit prediction) and other novel applications in the intersections of AI, machine learning/optimization and music. She is a senior member of the IEEE.^[4] In 2021 she was nominated to the Singapore 100 Women in Technology list,^[5] and her Mustango: Controllable text-to-music Project won the SAIL Award Top 30 at the World Artificial Intelligence Conference in Shanghai in 2024.^[6]

Herremans' research on dance hit prediction, automatic piano fingering and AI automatic music generation systems (e.g. MorpheuS) has received attention in the popular press, including international magazines such as Motherboard from Vice magazine,^[7] Channel News Asia's Documentary Algorithms Episode 1: "Rage Against The Machine",^[8] The San Francisco Examiner,^[9] Belgian national TV^[10] and Belgian and French national radio.^{[11] [12]}

Selected publications

• Melechovsky, J., Guo, Z., Ghosal, D., Majumder, N., Herremans, D., & Poria, S. (2024). Mustango: Toward controllable text-to-music generation. Proc. of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). Mexico City.
• Melechovsky, J., Roy, A., & Herremans, D. (2024). MidiCaps--A large-scale MIDI dataset with text captions. Proceedings of the International Society of Music Information Retrieval (ISMIR). San Francisco.
• A Functional Taxonomy of Music Generation Systems . Herremans D, Chuan CH, Chew E . 2017 . . 50 . 5 . 1-30.
• MorpheuS: generating structured music with constrained patterns and tension . Herremans D, Chew E . 2017 . IEEE Transactions on Affective Computing.
• Modeling temporal tonal relations in polyphonic music through deep networks with a novel image-based representation . Chuan CH, Herremans D . April 2018 . Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence.
• Machine learning research that matters for music creation: A case study . Sturm BL, Ben-Tal O, Monaghan Ú, Collins N, Herremans D, Chew E, Hadjeres G, Deruty E, Pachet F . 2019 . Journal of New Music Research . 48 . 1 . 36-55.
• From context to concept: exploring semantic relationships in music with word2vec . Chuan CH, Agres K, Herremans D . 2020 . Neural Computing and Applications . 32 . 4 . 1023-1036.
• Singing voice separation using a deep convolutional neural network trained by ideal binary mask and cross entropy . Lin KW, Balamurali BT, Koh E, Lui S, Herremans D . 2020 . Neural Computing and Applications . 32 . 4 . 1037-1050.
• Composing fifth species counterpoint music with a variable neighborhood search algorithm . Herremans D, Sörensen K . 2013 . Expert Systems with Applications . 40 . 16 . 6427-6437.
• Dance Hit Song Prediction . Herremans D, Martens D, Sörensen K . 2014 . Journal of New Music Research, Special Issue on Music and Machine Learning . 43 . 3 . 291-302.

Notes and References

1. Web site: Dr. Dorien Herremans, Assistant Professor . Singapore University of Technology and Design.
2. Web site: Meet The Team . SUTD Game Lab.
3. Web site: Hybrid Machine Learning – Optimization techniques To Generate Structured Music Through Morphing And Fusion . CORDIS.
4. Web site: Dorien Herremans . IEEE . 2022-02-03 .
5. Web site: SG100WIT 2021 List - Citations . Singapore Computer Society . 3 February 2002 . 22 January 2023 . https://web.archive.org/web/20230122023620/https://www.scs.org.sg/sg100wit-2021-list-citations . live.
6. Web site: Congratulations to Associate Professor Dorien Herremans on winning the SAIL WAIC Award Top 30 . 2024-07-27 . Information Systems Technology and Design (ISTD) . en-US.
7. Web site: A Machine Successfully Predicted the Hit Dance Songs of 2015 . Neal . Meghan . 17 December 2015 . Motherboard.
8. Rage Against The Machine . Algorithms . Channel NewsAsia . 1 October 2018 . 1 . 1.
9. News: The Bleeding Edge: The Center for New Music Launches a New Concert Series . Smoliar . Stephen . 4 May 2016 . The San Francisco Examiner . Elaine Chew Blog.
10. Web site: Op een wetenschappelijk verantwoorde manier te weten komen of je een dance-hit hebt gemaakt of niet? . Would you like to find out in a scientifically responsible way whether you have made a dance hit or not? . 1 December 2014 . Reyers Laat . nl . Dorien Herremans.com.
11. Web site: Comment prédire qu'une chanson sera un tube? . How do you predict that a song will be a hit? . fr . Rozec . Thomas . 26 November 2014 . France Info.
12. Web site: ANT/OR - Radio 2 - FuX-app genereert muziek in de stijl van Bach, Beethoven en Haydn . ANT/OR - Radio 2 - FuX app generates music in the style of Bach, Beethoven and Haydn . nl . Herremans . Dorien . 23 February 2013 . YouTube.