“Our new all-neural, on-device Gboard speech recognizer is initially being launched to all Pixel phones in American English only,” wrote Johan Schalkwyk, a Google fellow of its Speech Team, in a blog post. “Given the trends in the industry, with the convergence of specialized hardware and algorithmic improvements, we are hopeful that the techniques presented here can soon be adopted in more languages and across broader domains of application.”
While voice recognition on smartphones is nothing new, there is always a slight delay when virtual assistants — such as Siri, Alexa and Google — respond to a user’s query. That happens because the data from the user’s voice has to travel from their phone to the servers of the service provider, where it is then analyzed and sent back. However, Google’s new technology is an end-to-end speech recognizer, compact enough to be kept on a phone.
“This means no more network latency or spottiness — the new recognizer is always available, even when you are offline,” explained Schalkwyk. “The model works at the character level so that, as you speak, it outputs words character by character, just as if someone was typing out what you say in real time, and exactly as you’d expect from a keyboard dictation system.”
It’s not surprising that Google is working to improve its voice recognition capabilities. Data shows that voice-activated devices have become an important product for consumers.
In the second annual edition of the PYMNTS and Visa How We Will Pay survey, 28 percent of all U.S. consumers reported owning a voice-activated device that was used to listen to music, check the weather and ask “fun questions.” More important, 27 percent used them to make a purchase in the seven days that the survey tracked their purchasing behavior.