Paper Title
GREETING ROBOT WITH VOICE RECOGNITION, NAME IDENTIFICATION, AND FACE DETECTION

Abstract
This paper introduces an intelligent, fully integrated greeting robot capable of delivering seamless, real-time, personalised human–robot interaction through the tight coupling of three demanding modalities: automated face recognition, offline speech-to-text transcription, and context-aware text-to-speech synthesis. The system reliably identifies individuals under challenging real-world conditions, including variations in illumination and head pose. Once a person is recognised, the robot immediately generates a spoken, personalised greeting and transitions into an active listening mode. Spoken inputs such as “Hello,” “Good morning,” or “How are you?” are detected, transcribed offline, and answered naturally, with the response explicitly addressing the individual by name. The complete interaction pipeline executes in real time on embedded edge hardware without reliance on cloud services. A physically fabricated robot body integrates the camera, microphone, and speaker into a single, cohesive unit, resulting in a human-facing interactive agent rather than a purely software-based prototype. The system is designed for deployment at institutional entrances, campuses, and smart reception areas. Experimental evaluation demonstrates robust face identification, accurate offline speech recognition, and natural, contextually appropriate responses, confirming the practicality and effectiveness of this fully embodied, multimodal human–robot interaction framework. Keywords - Greeting Robot, Face Recognition, Voice Recognition, Human-Robot Interaction, Computer Vision, Speech Recognition, Text-to-Speech Synthesis