I'm an AI Engineer and Researcher passionate about building intelligent systems that understand and interact with humans naturally.
I have solid experience working on speech technologies, including:
- Automatic Speech Recognition (ASR)
- Speaker Verification (SV)
- Text-to-Speech (TTS)
- Audio Large Language Models (Audio LLMs)
I enjoy designing callbot center solutions, conversational AI, and human-robot interaction systems, where the ability to process and generate natural speech plays a critical role.
During my university years, I worked extensively on computer vision and deep learning, focusing on:
- Image segmentation
- Image classification
- Few-shot segmentation
- Object detection
This foundation helped me develop strong skills in designing and fine-tuning large-scale models, as well as integrating them into real-world applications.
On the research side, I'm interested in:
- Reasoning with LLMs
- Reinforcement Learning (RL) for optimizing conversational strategies
- Retrieval-Augmented Generation (RAG) for enhancing knowledge-grounded dialogue systems
My technical background spans both model development and deployment, covering end-to-end speech pipelines, advanced audio feature engineering, and multi-modal reasoning capabilities.
I always aim to bridge the gap between state-of-the-art research and impactful user-facing products — from scalable voicebots for customer service to advanced vision and speech-based interactive systems.
- ASR, SV, TTS, Audio LLMs
- Callbot / contact center automation
- Human-robot interaction
- Computer vision (segmentation, classification, few-shot segmentation, object detection)
- Reasoning and RAG with LLMs
- Reinforcement Learning for dialogue optimization
- 🌍 Based in Hà Nội, Việt Nam
- ✉️ Email: phamviettien130102@gmail.com
⭐ Feel free to check out my repositories and connect with me!
