/dqc/media/agency_attachments/3bO5lX4bneNNijz3HbB7.jpg)
Follow Us/dqc/media/post_banners/wp-content/uploads/2023/07/Voice-assistant.jpg)
Staqu Technologies, a developer of AI solutions, has unveiled its AI-enabled Voice Assistant System – Jarvis Help. The innovative technology utilises voice commands, gestures and hand waves to activate its functionality. This advanced system is designed to receive and interpret visual and audio directives, promptly notifying the appropriate stakeholders in real time.
Jarvis Help has the potential to provide enhanced risk identification in rescue systems in alignment with human behavior, to leverage real-time audio and video inputs and analyse hand motions, facial expressions and gestures indicative of assistance requirements.
Additionally, Jarvis Help has been supported by the world’s most accurate audio setup with an accuracy level of 98.7 percent, backed by the International Conference on Acoustics, Speech and Signal Processing (ICASSP) and VoxCeleb. The technology mainly being used to identify any one with voice sample and the same time can also be used to identify wake up words like "Jarvis Help" coming from any audio streaming device.
In critical situations like rescue, stuck in lift, kidnappings or robberies, this voice assistant system serves as a life-saving solution. It swiftly responds to distress calls by detecting signs of violence or assistance and immediately notifying the relevant authorities in real time. Whether through analysing audio and visual cues or recognizing gestures like waving or signaling for help within the camera’s range, Jarvis Help acts as a vigilant guardian, ensuring rapid assistance when victims need it most.
Additionally, this voice assistant system can identify indicators of danger even when there are no apparent physical signs of violence.
According to Atul Rai, Co-founder and CEO of Staqu Technologies, "As a responsible corporation, it is a privilege to develop an innovative technology that enhances our communities to become more futuristic and safer. Our pioneering technology in AI-enabled Voice Assistance Systems, Jarvis Help can significantly contribute to our long-term goal. By combining voice recognition and real-time video analysis on existing CCTV, Jarvis Help will be an intuitive and efficient solution for addressing rescue and safety needs for our citizens. Our contribution to creating a smarter and safer ecosystem through advanced AI technology can become a reality.”
The core focus of Jarvis Help is to comprehend human language and provide accurate outcomes by decoding visual or voice commands. Through continuous algorithmic improvements, it delivers analytical insights and promptly notifies the relevant authorities, thereby improving the operational efficacy of apt authorities. Moreover, the system can potentially employ a combination of AI and automation, enabling the deployment of drones to track individuals and gather crucial audio and video inputs as well. This interaction between Jarvis Help and humans mirrors the way two individuals communicate, encoding and decoding messages through gestures or voice commands.
The accuracy level of audio analytics being used in Jarvis Help is based on the idea of using CCTV cameras to record ambient audio data from beyond their field of vision in order to spot any disturbances or out-of-the-ordinary events and immediately trigger appropriate tactical reactions. For instance, the sound of breaking glass outside a physical store may be a sign of ongoing robberies, vandalism, or sabotage, whereas the sounds of gunshots, screaming, or loud shouting typically indicate physical violence and a serious threat to life.
The introduction of JARVIS Help holds significant potential for rescue systems and the development of smart city ecosystems. By incorporating advanced AI-enabled surveillance technology, JARVIS Help can effectively monitor illegal activities or ensure the safety of individuals. This innovative solution contributes to the establishment of safer and more secure communities.