Powerful AI and Edge-to-Cloud Speech Recognition

Sensory’s powerful AI technologies not only provide consumers with the convenience of voice-based interaction at home, but can also enable smart devices to alert us of things happening within our homes that we may not hear, safeguarding our homes and families from dangerous situations. Sensory’s TrulyNatural Speech-to-Text (STT) technology operates on the edge, offering unrivaled accuracy in a compact package. This edge-based processing can be seamlessly integrated with cloud services for more complex tasks, providing a hybrid approach that balances local responsiveness with cloud-based capabilities.

Image Alt Text

Sensory's Consumer & Home Electronics Customers

“The smartest TV ever deserves the smartest approach to privacy. With Telly’s use of Sensory’s on-device voice technology, we are able to bring extremely fast, low-latency voice commands to the living room."

Sascha Prueter
Chief Product Officer
Telly
Image Alt Text

Advantages of Edge-Based Voice Recognition

  • Enhanced Privacy: Voice data is processed locally, reducing the risk of sensitive information being transmitted over the internet.
  • Reduced Latency: Local processing significantly decreases response times, leading to more natural user interactions.
  • Lower Costs: By minimizing cloud dependencies, edge processing can reduce operational costs associated with constant data transmission and cloud processing.
  • Offline Functionality: Devices can perform voice recognition functions without relying on an internet connection.
Image Alt Text)

The Voice-Controlled Smart Home

A domain-specific embedded assistant can be used for device control using natural language. For example, a thermostat you can talk to (“Hey Thermostat increase the temperature to 69 degrees”), confirmation (“Temperature set to 69 degrees”), queries (“What is the room temperature?”), and information retrieval (lighting, user guides, etc). Sensory’s suite of embedded speech and biometric technologies can achieve this and more while keeping voice data private and secure; voice requests never leave the device, nor are they ever stored.

Sensory’s solutions are designed to work seamlessly with various home wireless protocols, including Matter, Zigbee, Wi-Fi, Bluetooth, and Thread. This multi-protocol support ensures compatibility with a wide range of smart home ecosystems and devices.

Image Alt Text)

Home Security & Safety

TrulySecure Sound ID is capable of recognizing a variety of environmental sounds, including glass breaking, babies crying, dogs barking, home security alarms, smoke/CO alarms and low battery warnings, doorbells, knocking, snoring and more. Consumer devices could instantly warn users when these sounds occur and send the owner sound clips to better understand the situation.

 

Image Alt Text)

Stay Connected

Get the latest speech recognition and artificial intelligence resources and industry updates.