Selected work
Production systems, research, and technical explorations spanning conversational AI, speech synthesis, and audio processing.
A production voice agent: streaming bidirectional audio, sub-second turn latency, and multi-turn speech interaction, grounded in cognitive-science immersion methodology.
Live in production on the App Store and Google Play, with sub-second turn-taking and streaming TTS.
On-device text-to-speech for React Native — local inference, no server round-trip, private by default.
A text-to-speech system that conditions prosody and emotional expression on visual cues, producing more natural, context-aware synthesized speech.
An AI-driven workflow that generates high-quality TTS training datasets, removing the data bottleneck for expressive speech models.
A GPT-2 language model implemented from scratch in PyTorch, trained to generate Shakespeare-style text.
Real-time music style transfer using RAVE (Realtime Audio Variational autoEncoder) for creative audio manipulation.
Audio stem separation using Spleeter and HT-Demucs for high-quality vocal and instrumental isolation.
A framework for evaluating and improving Chain-of-Thought reasoning in LLMs, using causal mediation analysis and faithfulness measurement.