Gollapalli, Parwateeswar and Tabasum, Sana and Tadaboina, Sidhartha and Ganta, Sai Kumar and Gottipamula, Aishwarya (2025) Wave Talk: A smart gesture and voice assistant. World Journal of Advanced Engineering Technology and Sciences, 15 (2). 073-081. ISSN 2582-8266
![WJAETS-2025-0512.pdf [thumbnail of WJAETS-2025-0512.pdf]](https://eprint.scholarsrepository.com/style/images/fileicons/text.png)
WJAETS-2025-0512.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.
Abstract
Wave Talk is a multimodal human-computer interaction system that integrates real-time hand gesture recognition and voice command processing to enable seamless, touchless control of digital devices. Utilizing OpenCV and Media Pipe for gesture tracking, alongside Speech Recognition and pyttsx3 for voice interaction, the system offers an intuitive interface accessible to users across diverse environments, including those with physical disabilities or in hygiene-sensitive settings. Designed to run on standard webcams and microphones, Wave Talk ensures cost-effectiveness and broad usability. The methodology encompasses data acquisition, preprocessing, model integration, and action execution, with system testing confirming high accuracy and low latency. Applicable in smart homes, healthcare, education, and public spaces, Wave Talk demonstrates the potential of multimodal interaction systems to enhance accessibility, efficiency, and user experience in next-generation smart technologies.
Item Type: | Article |
---|---|
Official URL: | https://doi.org/10.30574/wjaets.2025.15.2.0512 |
Uncontrolled Keywords: | Gesture Recognition; Voice Assistant; Multimodal Interface; Media Pipe; OpenCV; Speech Recognition; Touchless Control; Real-Time Interaction |
Depositing User: | Editor Engineering Section |
Date Deposited: | 04 Aug 2025 16:27 |
Related URLs: | |
URI: | https://eprint.scholarsrepository.com/id/eprint/3377 |