Lauri Juvela is an Assistant Professor at Aalto University with nine years of experience developing machine learning methods for real-time speech and audio applications. His research focuses on generative deep learning for speech synthesis, modification, and representation learning, with additional emphasis on efficiency and controllability via differentiable signal processing and self-supervised methods. He transitioned from industry research at Neural DSP Technologies to academia after completing a PhD in Speech and Language Technology, and his doctoral work on deep learning and signal modeling for TTS is publicly available. Based in Helsinki, he blends rigorous signal-processing foundations with practical, real-time system considerations—often targeting low-latency, controllable synthesis rather than purely perceptual gains.
9 years of coding experience
7 years of employment as a software developer
Doctor of Science (Technology), Electrical Engineering, Speech and Language Technology, Doctor of Science (Technology), Electrical Engineering, Speech and Language Technology at Aalto University
Bachelor of Science (BS), Signal Processing, Bachelor of Science (BS), Signal Processing at Aalto-yliopisto
GlottDNN vocoder and tools for training DNN excitation models
Contributions:168 commits, 2 PRs, 5 pushes in 4 years 5 months
pytorchdeep-learningtrainingvocoderdnn
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.
Request Free Trial
Lauri Juvela - Assistant Professor at Aalto University