Daniel Wolff

Daniel Wolff is a researcher affiliated with City University London, specializing in computational music similarity modeling and big data applications in musicology. His work bridges machine learning, audio signal processing, and music theory to analyze large-scale music collections.

• Doctoral thesis (2014): Spot the Odd Song Out: Similarity Model Adaptation and Analysis using Relative Human Ratings
• Key research focus: Adaptive similarity metrics, chord progression mining, and dataset automation
• Active in conferences like ISMIR, ACM Digital Libraries, and Interdisciplinary Musicology workshops

Research Trends: His publications emphasize:

• Big data infrastructure for musicological research
• Machine learning techniques for audio feature extraction
• Interactive visualization of harmonic patterns
• User-driven similarity modeling via comparative ratings

Technical Contributions: Developed uncertainty sampling methods for dataset curation, parallel computing approaches for chord analysis, and reproducible frameworks for music similarity evaluation.