03Research & Experiments

Questions I would rather test than assume.

I explore questions at the intersection of machine learning and human creativity. My research investigates how models interpret musical emotion across different audio contexts, and how AI-assisted ideation influences the originality and ownership of human creative work.

01 Done · 02 In progress

  • Machine learning
  • Music emotion
  • Human–AI creativity
Read the investigations
The valence–arousal plane, with an audio trace drawn underneath. Not a plot of songs or of model output.

Investigations

02 investigations

01 In progress · 01 Done

In progress

Planning and literature review. The files are in hand, and they are not yet ready for training.

02

In progress

Beyond Genre Classification: Evaluating Machine Learning Models for Music Emotion Recognition Across Instrumental and Vocal Audio

Music information retrieval · Machine learning · Music emotion recognition · Comparative model evaluation

How does music emotion recognition differ between instrumental audio and music that includes vocals?

Planning and literature review. The DEAM audio, annotations, and features are downloaded. They are not validated, cleaned, or ready for training.

Read the investigation
The valence–arousal plane, with an audio trace drawn underneath. Not a plot of songs or of model output.

Done

The evaluation has been carried out. Done is the state of the study, not a venue or a DOI.

01

Done

Beyond the Prompt: Measuring the Effects of AI-Assisted Ideation on Human Creative Originality and Ownership

Human–AI interaction · Computational creativity · Generative AI · Creative cognition and perceived ownership

How does AI-assisted ideation change the originality of human creative work, and the sense of owning it?

Empirical study and evaluation framework completed. Originality, self-reported ownership, and perceived agency were measured across unaided and AI-assisted conditions.

Read the investigation
Unaided and assisted ideation, held against the same three measures. Not a score chart.

Have an idea...

Have something to build.