Matthew Maciejewski
Research Scientist at The Johns Hopkins University
Washington, District of Columbia, United States
Summary
👤
Senior🎓
Top SchoolMatthew Maciejewski is a research scientist with a decade of experience specializing in speech and audio signal processing and machine learning, currently working at Johns Hopkins University. He focuses on waveform-level and conversational speech processing, particularly for far-field, noisy, and reverberant environments, building on prior research roles at Amazon and internships at MERL. Matthew blends deep academic training—a PhD in Electrical Engineering from Johns Hopkins—with practical engineering, contributing backend fixes, refactors, and a CallHome ivector-based diarization recipe to the widely used Kaldi open-source ASR toolkit. His work bridges algorithm development and production-ready tooling, with a knack for debugging subtle signal-processing issues like VAD and likelihood calculations. Based in Washington, DC, he brings both rigorous research methodology and hands-on DevOps experience to deploying robust speech systems.
10 years of coding experience
2 years of employment as a software developer
Johns Hopkins UniversityBachelor of Science (B.S.), Electrical and Computer Engineering, Bachelor of Science (B.S.), Electrical and Computer Engineering at Carnegie Mellon University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
kaldi10
speech-recognition10
c-language10
shell10
cprogramming-language10
scripting10
speaker-verification9
python9
cuda5
Programming languages (4)
Github contributions (5)
kaldi-asr/kaldi
Apr 2016 - May 2021
kaldi-asr/kaldi is the official location of the Kaldi project.
Role in this project:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:7 PRs, 29 comments in 5 years 1 month
Contributions summary:Matthew's contributions focused on bug fixes, refactoring code, and adding a new diarization recipe. The user fixed a bug in voice activity detection, and modified the LogLikelihoodRatio function. The user also implemented an ivector-based diarization recipe for CallHome, including feature extraction and PLDA scoring, and updated existing scripts. Furthermore, the user addressed a rounding issue in a utility script.
cudakaldiasrspeech-to-textkaldi-asr
mmaciej2/mmaciej2.github.io
Jan 2021 - Dec 2022
Contributions:26 commits, 30 pushes, 1 branch in 1 year 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.