Ken Schutte

Machine learning researcher, software developer, PhD

Chicago, IL, USA 🇺🇸 | Antigua, Guatemala 🇬🇹 | 🌍

Contact me for possible full- or part-time work. I enjoy solving difficult problems. Areas where I have spent significant time include,

• Speech, audio, and language. Speech-to-text, text-to-speech, machine translation, language modeling, audio processing.
• Computer vision. Image and video. 2D and 3D.
• Geospatial analysis. Raster and vector data processing, map projections, GIS formats.
• Text and documents. Internals of PDF, PostScript, SVG, Unicode details, typesetting, font formats.

Education:

• PhD, Massachusetts Institute of Technology (MIT), Electrical Engineering and Computer Science (EECS), Computer Science and Artificial Intelligence Labratory (CSAIL), 2009. Research in machine learning and speech recognition. Minor in computational neuroscience.
• Master of Science (SM), MIT, EECS, Advanced Telecommunications and Signal Processing Group, Research Labratory of Electronics (RLE), 2003. Research in speech processing and intelligibility.
• B.S. University of Illinois, Electrical Engineering (ECE), 2001. Focus on digital signal processing (DSP). Minor in Computer Science.

A few projects / writings / etc: [RSS Feed]

• 2023/08/07 swap_8_and_9: How a simple import can modify the Python interpreter.
• 2023/07/28 "Gzip beats BERT?" Part 2: dataset issues, improved speed, and results.
• 2023/07/26 Did Musk steal his new X logo?: glyph analysis in Python
• 2023/07/21 Learning PostScript by comparing it to Python
• 2023/07/17 Bad numbers in the "gzip beats BERT" paper?
• 2023 Guatemalan election: in-progress data analysis.
• 2023 Eurail trip: review coming soon.
• Phingerprint: An experiment in audio-fingerprinting on 4,240 hours of live Phish recordings.
• PhD Thesis: Parts-based Models and Local Features for Automatic Speech Recognition.
• MIDI processing in MATLAB.
• IPostScript: jupyter kernel for the PostScript language.
• Apple TV App for Democracy Now!.