Zoom Releases Edge Speech Recognition Powered by Sensory

July 9 2021, 00:50
Sensory announced the integration of its TrulyNatural embedded speech recognition software within the latest public beta release of Zoom Rooms for Android, iOS, MacOS and Windows. With this integration, voice commands are now supported on all Zoom Rooms platforms, which now offer the convenience of voice control while maintaining privacy. With this update, Zoom-native voice commands support expanded functionality, all processed locally, never in the cloud.
 

Zoom Rooms participants can now use their voice to ‘wake’ the room system by saying "Hello Zoom," as well as use commands such as ‘start meeting’, ‘leave meeting’, ‘check in’ and more, further empowering organizations to create safe, private, and effective hands-free meetings.

TrulyNatural is Sensory’s highly accurate, deep neural network-based, embedded speech recognition platform with natural language understanding. Zoom and Sensory have worked together to leverage the capabilities of TrulyNatural to create domain-specific recognizers designed to handle common voice requests for controlling meetings. They have also developed more complex voice tasks like alphanumeric recognition for using voice to enter meeting IDs and passcodes.

“Zoom understands the important role privacy plays to enterprise customers and selected Sensory to bring the convenience of voice control to Zoom Rooms. Utilizing our advanced embedded voice AI stack, we’ve bolstered the voice experience while maintaining total privacy and brand recognition,” says Todd Mozer, CEO at Sensory.

“Zoom is passionate about making collaboration easier, but we always put our customer’s privacy and security front and center,” states Cynthia Lee, Lead Product Manager at Zoom. "Sensory’s technology checked all the boxes for us: accurate, fast and private. We look forward to adding more voice features as our public beta progresses towards full launch later this year."

Sensory’s technologies are already widely deployed in consumer electronics applications including mobile phones, automotive, wearables, toys, PC’s, medical products, and various home or office electronics. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition.
 

Zoom is constantly improving the voice recognition, voice to text transcription and translation capabilities available in its platforms. Recently, Zoom Video Communications, announced a definitive agreement to acquire Karlsruhe Information Technology Solutions - Kites GmbH, a start-up dedicated to developing real-time Machine Translation solutions.

Kites was founded in 2015 and has academic roots with Karlsruhe Institute of Technology, where co-founders Dr. Alex Waibel and Dr. Sebastian Stüker are faculty members. Kites’ team of 12 research scientists will help Zoom’s engineering team advance the field of Machine Translation to improve meeting productivity and efficiency by providing multi-language translation capabilities for Zoom users. The Kites team remains based in Karlsruhe, Germany. Zoom is exploring opening an R&D center in Germany in the future.
www.sensory.zoom.us
www.sensory.com
Page description
About Joao Martins
Since 2013, Joao Martins leads audioXpress as editor-in-chief of the US-based magazine and website, the leading audio electronics, audio product development and design publication, working also as international editor for Voice Coil, the leading periodical for... Read more

related items