Perception • Computer Vision • HRI

Hi, I'm Amir Mohammad
Saberi

AI & Robotics Engineer specializing in Multimodal Perception & Human–Robot Interaction.

I design and deploy intelligent systems that fuse vision, audio, and context to enable machines to understand who is speaking, how humans feel, and when to act — from research prototypes to real-time robotic applications.

Amirmohammad Saberi Portrait
Core Domains & Architecture

Multimodal Perception & Systems

From micro-expression analysis to social robotics and edge hardware deployment.

Multimodal Active Speaker Detection

Real-time systems that combine audio cues (voice activity, pitch) and visual signals (lip motion, gaze) to accurately identify the active speaker in multi-person environments.

Applications: Social robots, smart meetings, collaborative systems
Audio-Visual Fusion

Human–Robot Interaction

Developed perception pipelines for Pepper robots enabling:

  • Emotion recognition
  • Context-aware responses
  • Natural, human-centric interaction
Focused on making robots socially aware, not just reactive.

Speaker Diarization & Audio AI

Context-aware diarization using acoustic features and BERT embeddings to handle overlapping speech in real-world conversations.

BERT + Acoustic Vectors

Computer Vision Systems

From micro-expressions to fatigue detection: CNN-LSTM architectures, facial cues, blink rate, and real-time vision pipelines.

Security & Psychology

Research to Real-Time Deployment

PyTorch, OpenCV, MediaPipe, NVIDIA Jetson, AWS Panorama. Edge-ready, low-latency systems bridging theory and hardware.

Edge AI & Embedded Systems
Portfolio Showcase

Featured Projects

Detailed research implementations in computer vision, robotics perception, and multimodal learning.

Active Speaker

Multimodal Active Speaker Detection

Computer Vision Audio Processing Deep Learning

Built a real-time system that fuses audio cues and visual signals to identify who is speaking in multi-person conversations, improving robustness in noisy and dynamic environments such as social robots and smart meetings.

Research Prototype Audio-Visual Model
Pepper Robot

Autonomous Social Robot with Emotion Recognition

Robotics HRI Computer Vision Emotion AI

Developed perception pipelines for a Pepper robot to recognize basic human emotions and respond with context-aware behavior, enabling more natural and socially aware human–robot interaction.

Physical Robotics Social AI
Audio AI

Speaker Diarization & Audio Intelligence

Audio AI NLP Diarization

Designed a speaker diarization pipeline combining acoustic features with language embeddings to accurately determine who spoke when, even in overlapping and multi-speaker conversations.

Conversational AI Overlap Diarization
HRI Safety

Multimodal Fatigue Detection for HRI

HRI Computer Vision Deep Learning

Built a real-time fatigue detection system by fusing visual indicators (blink rate, yawning) and speech patterns to help collaborative robots adapt task pace and improve human safety and comfort.

Collaborative Robotics Fatigue Adaptation
Accessibility

Real-Time Sign Language Translator

Computer Vision Deep Learning HRI

Developed a system that translates sign language gestures into speech using hand keypoint detection and sequence models, enabling more accessible communication between humans and robots.

Gesture AI Hand Keypoints
Affective AI

DecepVision – Lie Detection via Micro-Expressions

Computer Vision Affective Computing Deep Learning

Built a deep learning system to detect deception by analyzing micro-expressions in video streams, focusing on subtle and involuntary facial movements relevant to psychology and security research.

Micro-Expression Analysis Facial Dynamics
CLI Sandbox

Interactive Terminal

Run commands directly or click the preset chips below to explore Amir's bio, skills, and background.

saberi-terminal — zsh
Welcome to Saberi.pro interactive shell. Feel free to explore!
Type help to list available commands, or click the buttons above.
guest@saberi.pro:~$ whoami
Amir Mohammad Saberi — AI & Robotics Perception Engineer
guest@saberi.pro:~$

Technical Stack & Tooling

Technologies, frameworks, and hardware utilized across research and production.

Perception & AI
PyTorch OpenCV MediaPipe CNN-LSTM BERT AV Fusion
Robotics & HRI
Pepper Robot ROS Emotion AI Gaze Tracking HRI Adaptation
Hardware & Edge
NVIDIA Jetson AWS Panorama TensorRT Real-Time Video Edge AI
Engineering
Python C++ Linux Git & CI/CD Docker
Let's Collaborate

Get in Touch

Whether you're interested in AI/Robotics research, industrial collaboration, or consulting, feel free to reach out.

Copied to clipboard!