Scholar
Matthew Maciejewski
Google Scholar ID: 2uyMFk4AAAAJ
Johns Hopkins University
speech separation
speaker diarization
speaker identification
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
721
H-index
10
i10-index
11
Publications
20
Co-authors
0
Contact
Email
matt@mmaciejewski.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
3 items
Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams
2025
Cited
0
Unsupervised Speech Enhancement using Data-defined Priors
2025
Cited
0
Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2024
Cited
0
Resume (English only)
Background
Researcher specializing in speech and audio technology
Interested in processing conversations captured in ambient acoustic environments with multiple far-field speakers
Expertise in deep learning, statistical modeling, and signal processing
Focuses on waveform-level processing of acoustic signals
Primary research interests include speech enhancement, single-channel speech separation, speaker diarization, and speaker identification
Addresses challenges such as low volume, interference, reverberation, and overlapping speech in real-world recordings
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up