Vancouver AI startup Picovoice announced today that they have developed the world’s first real-time speech recognition engine that can run offline anywhere.
Voice user interfaces like Amazon Transcribe make it easy for developers to add speech-to-text capability to their applications thanks to cloud-based Speech recognition services.
Despite the ubiquity of speech-enabled devices, processing speech in the cloud has raised major privacy concerns with the uploading and handling of personal voice data. Cloud speech recognition also has fundamental limitations in terms of latency, reliability, and cost-effectiveness at scale.
Offline speech recognition has the potential to address these issues by eliminating the need for connectivity and tapping into readily available compute resources on billions of devices.
Picovoice has developed deep learning technology specifically designed to run speech recognition efficiently on commodity hardware with limited compute resources.
Picovoice’s bespoke voice AI technology enables Picovoice to run real-time speech-to-text on a $5 Raspberry Pi Zero or locally within a web browser. This lowers latency and cost while respecting user privacy by not requiring their speech data to leave their device.
Picovoice was founded by Alireza Kenarsari in 2017. Prior to founding Picovoice, Kenarsari worked as a senior software engineer at Amazon and has been an early engineer in multiple successful startups including Avigilon.
“Edge-based voice recognition is the next natural step in the architectural evolution of voice interfaces. A similar trend has already transformed the architecture of web applications, shifting functionality from servers to browsers. This has assisted in building applications that are responsive, context-aware, and scalable. I believe voice as an interface will go through the same evolution,” Kenarsari shared in today’s press release.
Picovoice routinely publishes open-source benchmarks for their products including their recent speech-to-text engine.
The benchmarks indicate that the software is matching the accuracy of major cloud providers such as Google and Amazon while running locally on a small embedded device.
Picovoice software is currently used by dozens of enterprise licensees, including LG and Whirlpool.