My Projects
Building innovative AI solutions that push the boundaries of what's possible
DIS-Vector
Zero-shot voice cloning framework via advanced speaker embedding extraction from limited audio samples.
EMOD: Emotional Speech Synthesis
Standalone emotion embedding extraction framework for neural TTS with continuous intensity control and zero-shot emotion transfer.
Real-time Conversational AI Agent
End-to-end conversational AI with streaming ASR, LLM reasoning, and neural TTS for real-time natural conversations.
Multimodal Vision RAG
CLIP-powered multimodal embedding pipeline with LLaVA reasoning for enterprise document intelligence.
Enterprise RAG Platform
Hybrid search RAG with knowledge graph traversal for 40% improved answer relevance over naive RAG.
Real-Time Object Tracker
ONNX-quantized YOLOv9 + ByteTrack deployed on edge hardware at 30fps for retail analytics.
Multilingual TTS Engine
Production TTS engine supporting 12 languages with sub-200ms first-token latency and custom prosody model.
Voice Cloning Studio
Professional voice cloning and synthesis platform supporting 20+ languages with emotion control.
ML Optimization Suite
Advanced optimization algorithms with convergence analysis and interactive visualizations.