People often confuse kinetics and kinematics. What are they, and which one can you derive from motion capture data? Kinematics Kinematic analysis concerns the geometric aspects of motion, including position, velocity, and acceleration. When dealing with motion capture, you typically get either position (from a camera-based system) or something similar to acceleration (from accelerometers). These are related, and since I have now figured out how to make equations here on the blog, here you get a summary of high school physics: ...
I see that the concept of “tempo octave” is being used by some researchers in the music information retrieval (MIR) community. This is a confusing term from a musical perspective. Here I explain why this is a bad idea. Octaves An octave is a core term in (Western) music theory related to describing intervals, relationships between two notes (and tones!) with a frequency ratio of 2:1. Here is an example of an octave: ...
Yesterday, I wrote about some reflections I had during Olgerta Asko’s PhD defence. Today, while chopping up the video recording to put on the RITMO web page, I thought that it might help to use a videogram to assist with segmentation. Videograms A videogram is similar to a motiongram, the main difference being that the videogram uses the regular video image as input to the “compression” instead of a motion video. Both give an impression of what is in a video file over time. We have functions for creating both videograms and motiongrams in the Musical Gestures Toolbox, but those are optimized for using also other functions in the toolbox. ...
Today, we had the PhD defence of Olgerta Asko at RITMO. Her research is super interesting in itself (check out this feature story for an overview). This blog post is following up on one of the points she made during her trial lecture that I hadn’t thought about before: the difference between generalisation, inference, and deliberation. Towards deliberation Olga argued that current AI—here understood as large language models (LLMs)—are based on generalisation. They extract patterns from a lot of data and apply them broadly. As we have seen with recent commercial products and as I have explored in many ways on this blog, LLMs excel at this task. ...
Yesterday, I wrote about the history and future of AI in general. Today, I am continuing my explorations by examining the role of AI in the arts and the impact of the arts on AI. The exploration is based on this notebook, with 60 sources collected by NotebookLM. AI in the Arts AI has a multi-generational history in the arts, transitioning from centuries-old mechanical automatons to symbolic rule-making and eventually to deep learning-based approaches. In the following, I will go through some of the works picked out by NotebookLM. Some of them I know well, others I hadn’t heard about before. A complete list of detected works is at the end of the post. ...
Due to MishMash, I am nowadays lecturing on AI, music, and creativity several times a week. I usually include a brief overview of machine learning history, mainly to explain that ChatGPT didn’t come out of nowhere but was the result of decades of research. To check that my story holds and to get a few more critical years and names in place. This blog post summarizes the brief history of AI to date. ...
I find Google’s NotebookLM to be one of the most powerful tools for researchers these days. Its core function is to work with the material you upload. Hence, it differs from ChatGPT and other tools that invent things on their own or search the web. It also has many different types of reports, including audio and video. But how accurate is it? Testing NotebookLM To test NotebookLM on some material I know very well, I decided to provide it with a collection of public data about myself, more specifically, what I have registered in the Norwegian NVA system, which is the database we use in Norway to register all our academic activities. This includes academic publications, public lectures, artistic works, interviews, etc. In my case, that contains around 1000 entries dating back to 2000. ...
Since I am on a roll with cleaning up my Hugo-based blog, adding alt text, and supporting math writing, I also had to experiment with adding support for musical scores. For the Sensing Sound and Music book, I used music21 in Python after struggling to set up LilyPond. Both LilyPond (professional engraving) and music21 (symbolic analysis and MIDI generation) are powerful and could be integrated into a blog, but they usually require a server-side toolchain or extra installation. However, with the help of CoPilot, I discovered ABCjs, a lightweight client‑side library that provides rendering, playback, and MIDI export, which work well for static sites. ...
Happy new year! As we move into 2026, I am currently undergoing a gradual shift in my academic life. I don’t have any new annual projects planned this year (like 365 Sound Actions or #StillStanding). This year is more about wrapping up old things and moving on with exciting new projects. I am more or less done with writing Still Standing, which summarizes 15 years of micromotion research. My AMBIENT project is also about to end, with sveral of my doctoral and postdoctoral fellows wrapping up their projects in the coming months. The plan is to write a book based on AMBIENT, too, summarizing my interest in indoor environments. However, book writing takes time, so it will probably take a few years before I have completed that project. ...
I am continuing to clean my Hugo site. Going over old posts, I found one on explaining artificial neural networks that included a bunch of equations based on screenshots from my master’s thesis. Now, with the help of CoPilot, I have implemented proper equation support on my Hugo site. KaTeX to the rescue I am used to writing my academic texts using LaTeX, an advanced typesetting library where you write code and compile it to a PDF (or something else). One of the benefits of LaTeX is its advanced support for typing equations (and many other features). However, until recently, it wasn’t so easy to write equations in HTML. ...