Taha Emara
Machine Learning Engineer @思科
Signup · Get unlimited contacts
WORK HISTORY
Machine Learning Engineer @思科
Scotland, GB
EDUCATION
Ain Shams University
Master of Science (MSc), Computer and Systems Engineering
El Shorouk Academy
Bachelor of Science (BS), Communications and Electronics Engineering
SKILLS
ABOUT TAHA EMARA
I’m a machine-learning engineer specializing in Audio AI, real-time speech enhancement, voice activity detection (VAD), single-talker isolation, and neural audio codecs, with 6+ years of experience building production-ready AI systems that bridge research and deployment.At Cisco (via the BabbleLabs acquisition), I contributed to Webex Smart Audio by delivering:• Voice Activity Detection, Noise Suppression & Speech Enhancement — improving clarity under noisy conditions• Single-Talker Isolation (“Optimize for My Voice”) — suppressing background speech so only the main speaker is heard clearly• Generative Neural Audio Codec — enabling high-quality, low-bandwidth voice for global Webex users• Cross-platform integration — including a ClearEdge macOS app for real-time noise and background-speech removalBeyond audio, I bring strong experience in computer vision, semantic segmentation, real-time inference pipelines, and edge/cloud deployment. While my current work is centered on Python and PyTorch for building and deploying ML models, I also have a strong software engineering background in C/C++, Java, and Objective-C. These skills strengthen my ability to integrate models into production systems, optimize performance, and bridge the gap between machine learning and real-world applications.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.