Publications

Research papers, technical reports, and open-source contributions

DIS-Vector: A Framework for Voice Intelligence and Speaker Embedding Extraction

Open-source Project 2024Citations: 5

A comprehensive framework for extracting speaker embeddings, emotional features, and prosodic patterns from limited audio samples, enabling zero-shot voice conversion and few-shot speaker adaptation.

Code Paper

Real-time Conversational AI: Integrating Streaming ASR, LLM Reasoning, and Neural TTS

Technical Report 2024Citations: 3

Architecture and implementation of end-to-end conversational AI systems with multilingual support, context persistence, and emotion-aware response generation.

Code

Advanced RAG Systems: Hybrid Search and Agentic Reasoning

Technical Report 2024Citations: 2

Novel approaches to retrieval-augmented generation combining dense and sparse retrieval with multi-document reasoning for enhanced accuracy.

Code