Scholarlink

This paper presents the design and implementation of an intelligent smart home control system that seamlessly integrates gesture recognition, speech processing, and mobile application interfaces. The system enables intuitive and flexible control of household appliances such as lights, fans, and irrigation units. Gesture input is handled using a Convolutional Neural Network (CNN) model trained via the TensorFlow Object Detection API. Speech commands are processed using the Google Speech-to-Text API, while manual operations are facilitated through a mobile application developed on the Kodular platform. Firebase ensures real-time data synchronization between modules, and the ESP32 microcontroller executes the hardware-level actions. The proposed solution enhances user convenience, accessibility, and system responsiveness. Experimental results demonstrate a recognition accuracy of 98% for gestures and 95% for voice commands, highlighting the system’s reliability and potential for future smart home deployments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Smart Home Control: Integrating Gestures, Speech, and Mobile Application

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mahendra Shridhar Naik,
  • Bandari Channapriya,
  • Shimmi Sahu,
  • Kolathur Supreeth Pranav,
  • Anisha Agarkhed,
  • Janhavi Parmar

摘要

This paper presents the design and implementation of an intelligent smart home control system that seamlessly integrates gesture recognition, speech processing, and mobile application interfaces. The system enables intuitive and flexible control of household appliances such as lights, fans, and irrigation units. Gesture input is handled using a Convolutional Neural Network (CNN) model trained via the TensorFlow Object Detection API. Speech commands are processed using the Google Speech-to-Text API, while manual operations are facilitated through a mobile application developed on the Kodular platform. Firebase ensures real-time data synchronization between modules, and the ESP32 microcontroller executes the hardware-level actions. The proposed solution enhances user convenience, accessibility, and system responsiveness. Experimental results demonstrate a recognition accuracy of 98% for gestures and 95% for voice commands, highlighting the system’s reliability and potential for future smart home deployments.