Summary
Toni Heittola is a Machine Learning Lead and researcher with two decades of deep expertise in audio content analysis, signal processing, and building scalable ML systems for real-world applications. Based in Tampere, Finland, he has led projects across smart city analytics, healthcare monitoring, and acoustic monitoring—bridging academic research with production deployments using PyTorch, Kubernetes, and edge/server prototypes. His work on Computational Auditory Scene Analysis and sound event detection combines foundational research, open dataset creation, and community building (notably helping grow the DCASE research community) to set benchmarks in the field. Toni’s background spans hands-on prototype deployment (RPi/Linux), zero-shot learning for audio, and practical solutions for loudspeaker nonlinearities, revealing a knack for turning niche audio science into deployable systems.
10 years of coding experience
21 years of employment as a software developer
Master of Science (MSc) Signal Processing (Speech and Audio), Master of Science (MSc) Signal Processing (Speech and Audio) at Tampere University of Technology 1965-2018
Doctor of Science in Technology Computing Sciences, Doctor of Science in Technology Computing Sciences at Tampere University
English, Finnish, Swedish, German