I’m an R&D Engineer working on applying ML to the voice synthesis, compression, and recognition space. Currently working on a communication device called Relay.
My background is in physics where I did research in computational quantum mechanics before moving into tech as a Site Reliability Engineer. I transitioned into R&D from there and have worked on problems ranging from indoor location tracking to log anomaly detection with a core focus on voice recognition and synthesis.
(In no particular order)
- autoregressive NNs
- manifold learning
- unsupervised/semisupervised learning
- speech synthesis and recognition
- software defined radios
- neural compression
- brain computer interfaces
- embedded systems
- on device ML/DL
- field programmable gate arrays
- distributed systems