Sponsored LinkedIn post
A dedicated post to introduce your brand to my audience.
Associate Professor @ Singapore University of Technology and Design (SUTD)
Companies pay Dorien to write a post about their product on LinkedIn or X.
This page is where they book it. Below: Dorien's audience, recent posts and price. Naano, the platform behind this page, handles the brief, your approval of the post and the payment.
€110per X post, fixed price
You approve the post before it goes live
Looking for Dorien? View LinkedIn profileView X profileA creator yourself? Create your own page
Associate Professor | Generative AI & Multimodal Intelligence | SAIL Top 30 | SG 100 Women in Tech
🚀 I’m an Associate Professor at SUTD and the founder of the Audio, Music, and AI Lab (AMAAI), where we pioneer generative and multimodal AI systems with real-world impact. 🤖 I built my first generative music AI model in 2004, and today, my team develops advanced systems like Mustango (text-to-music), Text2midi, and video2music—pushing the boundaries of how AI understands and creates. 🏆 Recognized as a Top 30 SAIL Award Finalist 2024 and one of the SG 100 Women in Tech 2021, I’m passionate about building trustworthy, creative, and impactful AI systems—and mentoring the next generation of innovators. 📬 I welcome collaborations on LLMs, generative AI, including multimodal FinTech application and creative AI.
LinkedIn export · Nov 21, 2025 – Nov 20, 2026 · Provided by the creator, not independently verified by Naano
X
Public X data · Captured Nov 20, 2026
𝗡𝗲𝘄: 𝗮 𝟭𝟯𝟮-𝗽𝗮𝗴𝗲 𝘁𝘂𝘁𝗼𝗿𝗶𝗮𝗹 𝗼𝗻 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗺𝘂𝘀𝗶𝗰 𝗮𝘂𝗱𝗶𝗼 🎶 A few years ago, generating a full song with vocals from a text prompt was unthinkable. In our review, we counted 25 song generation systems released in 2025 and 2026 alone. Prof. Mateusz Modrzejewski, Joanna frota Kurkowska and I wrote this tutorial to explain how they work. It explains codecs and autoencoders, token models, diffusion and flow matching, faster sampling and preference optimization in one notation, with worked examples from published systems. It then looks at what instrumental generation, full songs with vocals, editing and live performance each need from a model, and how to evaluate and release these models responsibly. It's written for students, researchers and engineers getting into the field, and for musicians who want to know what's behind the tools they're starting to use. Fast progress doesn't mean the field is done. Going through all these systems, we kept running into the same unsolved problems. 𝗪𝗵𝗮𝘁'𝘀 𝘀𝘁𝗶𝗹𝗹 𝗼𝗽𝗲𝗻: - Long-range structure. Models can now produce full-length songs, but no widely adopted protocol evaluates form, motif development and tension over several minutes. - Evaluation. Some systems use the same aesthetics predictor as a training reward and as the evaluation metric. A higher score can then just mean the model learned to please that judge. - Data and memorization. Most training data is undisclosed. Lyric filters miss phonetic memorization, and detectors for generated audio get worse after mixing or broadcast. - Coverage. Song models focus mostly on English and Mandarin pop. Most of the world's musical traditions are barely in the training data. - Interpretability. We know very little about how these models represent music internally, so control and safety interventions are still found by trial and error. Systems also differ so much in data, scale and evaluation that comparing them side by side says little about where the reported gains come from. Part of the tutorial is about learning to interpret those claims. Whether you're new to music generation or you want to fill in the gaps in what you already know, the full tutorial goes much deeper than this post can. 📕 Read full paper: https://lnkd.in/gbgMVNrB Mateusz Modrzejewski, Joanna Kurkowska, Dorien Herremans. A Tutorial on Generative Models for Music Audio. arXiv:2610.38252, 2026. #MusicAI #GenerativeAI #MachineLearning #MusicTech
The first emerging AI technologies for music workshop at AAAI ended up as a full PMLR volume. Round two is in Montréal. The deadline is 6 November. The 2nd Workshop on Emerging AI Technologies for Music (EAIM) will take place at AAAI-27, 22–23 February 2027. Last year’s papers from EAIM@AAAI, Singapore are in PMLR Volume 303: https://lnkd.in/guFE89YZ 𝗔𝗰𝗰𝗲𝗽𝘁𝗲𝗱 𝗽𝗮𝗽𝗲𝗿𝘀 𝘄𝗶𝗹𝗹 𝗮𝗴𝗮𝗶𝗻 𝗯𝗲 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 𝗶𝗻 𝗣𝗠𝗟𝗥 (Proceedings of Machine Learning Research), after double-blind review with three reviews per paper. This year’s theme is 𝗛𝘂𝗺𝗮𝗻 𝗮𝗴𝗲𝗻𝗰𝘆 𝗮𝗻𝗱 𝗰𝗿𝗲𝗮𝘁𝗶𝘃𝗶𝘁𝘆 𝗶𝗻 𝗰𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀. The question we want to explore is how to build music AI that musicians, producers, composers and educators can actually steer and shape, rather than simply accept what it produces. We welcome work on generation, foundation models for music, MIR, production workflows, performance systems, education, therapy, evaluation, and the ethical and cultural questions around all of this. Demos of AI instruments, interfaces and tools are encouraged, and so are strong conceptual and analytical papers. Papers are 8–11 pages in PMLR format, excluding references. At least one author presents in person. Keynote speakers: Gabriel Vigliensoni, Dominic Thibault (Université de Montréal) and Julia Werneburg (SOCAN). 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: 𝟲 𝗡𝗼𝘃𝗲𝗺𝗯𝗲𝗿 𝟮𝟬𝟮𝟲 (AoE) CFP and OpenReview link: https://lnkd.in/gF6eG3_4 Co-organised with Keshav Bhandari, Shuoyang Jasper Zheng, Jordie Shier and Simon Colton from Queen Mary University of London #AAAI2027 #MusicAI #MachineLearning #CallForPapers Association for the Advancement of Artificial Intelligence (AAAI)
Sampling, bit depth, lossless prediction, auditory masking and MP3, each worked by hand and then measured, and this is still not enough for a model that has to write the music itself. One second of CD audio is 88,200 numbers. A three-minute song is 15,876,000 of them. A language model writing a long essay produces a few thousand tokens. If we asked the same kind of model to write a song one audio sample at a time, it would have to stay coherent over a sequence thousands of times longer than anything it writes in text, and a single wrong number would be audible as a click. Every AI music generator gets around this in the same way. It never touches raw audio. It works on a compressed version, produced by a component called a codec, and most of what these systems can and cannot do follows from how that compression works. This is the first article in my guide to how AI music generators work, and it starts at the bottom of the stack. I will define each term when it first appears, work each idea with numbers small enough to check by hand, then measure it on real audio. The scripts behind every measurement are linked at the end.
Choose a format for your next LinkedIn collaboration.
A dedicated post to introduce your brand to my audience.
Reposts your LinkedIn post to my network.
Reposts your LinkedIn post with my own comment.
Choose a format for your next X collaboration.
A dedicated post to introduce your brand to my audience.
Quotes your X post with their own comment.
Your collaboration, managed on Naano
How does this price compare? B2B creator rates 2026
People who saw my posts, from my LinkedIn export.
People who saw my posts, from my LinkedIn export.
People who saw my posts, from my LinkedIn export.
People who saw my posts, from my LinkedIn export.
People who saw my posts, from my LinkedIn export.
X
Must be more cyberattacks 😅😅😅 https://t.co/b598Cn7sYv
So LemonSqueezy is winding down. Question for everyone: Migrate to Striped Managed Payments or Paddle. Had a great experience setting up Paddle recently with a project.
https://t.co/f7X2OvCcri
Correct me if I am wrong: - Vibe coding: using older small context models to code one task at a time, lots of reading and decisions for us. - Agentic engineering: multi-agent setups with harnesses producing better then human output.
Perfect Friday. No emails.
Storefront by Naano · Create yours
Dorien Herremans is a B2B LinkedIn creator based in Singapore with 4,052 followers, posting about AI, Data / Analytics, and Developer Tools. On Naano, one sponsored LinkedIn post by Dorien Herremans costs €417, a fixed price per post. A sponsored X post costs €110.
The Naano team casts the creators, writes the briefs, reviews every draft with you and reports results per creator. You approve the shortlist and every draft.