PRESS RELEASE

Picovoice unveils its web platform for designing edge-first voice experiences


December 4, 2019 (VANCOUVER, BRITISH COLUMBIA) - Picovoice unveils its web platform for designing edge-first voice experiences and announces partnership with ARM. The platform supports training universal wake words and domain-specific natural language understanding (NLU) skills that run entirely offline—even on tiny microcontrollers.

To create speech models using Picovoice, users do not need to provide audio training data; they simply type in phrases. By using proprietary transfer learning technology, the platform removes the data collection burden and shortens training time from weeks to hours. This reduces training costs by an order of magnitude while surpassing the accuracy of alternative solutions [1-3].

“The platform creates new opportunities for companies to offer private and personalized voice experiences while retaining control of their brand,” said Mehrdad Majzoobi, VP of Strategic Partnerships at Picovoice. “Our AI partnership with ARM accelerates our vision of embedding Picovoice technology in billions of edge devices.”

The web platform introduces an NLU designer to build voice interfaces that infer user’s intent directly from speech. Customers can use the web console to rapidly prototype, iterate, and validate—without having to write a single line of code. This makes building offline voice interfaces with Picovoice as approachable as cloud-based offerings, without a cloud dependency.

“The Picovoice Console lets our customers build sophisticated speech models without domain expertise,” says David Bartle, VP of Software at Picovoice. “You can focus on designing a voice interface without thinking about signal analysis or machine learning.”

The Picovoice platform scales automatically to handle model training workloads. Trained speech models can be exported to run on a wide range of devices, including a number of ARM Cortex-M microcontrollers [4] and Cortex-A microprocessors [5]. Additionally, Picovoice runs on Raspberry Pi, BeagleBone, iOS, Android, Linux, macOS, Windows, and even modern web browsers [6].

Try the Picovoice Console to generate custom speech models at https://picovoice.ai/console/, for non-commercial evaluation. For commercial applications, contact the Picovoice enterprise team [7]. Picovoice is a Canadian technology startup based in Vancouver, British Columbia. To learn about Picovoice, visit us on the web at https://www.picovoice.ai.