Articles on TechRepublic - Thursday, May 9, 2019 at 12:55 PM
On-device speech recognition may make smart assistants more appealing
Google unveiled the next-generation Google Assistant at I/O 2019, featuring an
on-device speech recognition model-bypassing the need to upload voice samples
to cloud systems.
Google and Amazon definitely want people to bring smart assistant speakers like
the Google Home and Amazon Echo into their homes—the lower-end versions of the
two, the Google Home
Mini<https://www.cnet.com/reviews/google-home-mini-review/> and Amazon Echo
Dot<https://www.cnet.com/reviews/amazon-echo-dot-third-generation-review/>, are
frequently heavily discounted or bundled with other products or services to the
point they have become the digital age's equivalent of the free toy in the
bottom of the cereal box.
There are—naturally—holdouts against this type of technology, given the
relative discomfort people have with bringing an internet-connected speaker
that constantly listens for the "wake word" used to prompt the device to spring
into action in their home. Anecdotes abound, such as a Portland couple claiming
their Echo arbitrary recorded and send a conversation to someone in their
contact
list<https://www.techrepublic.com/article/no-alexa-isnt-spying-on-you-but-be-careful-with-sensitive-conversations/>.
Despite resistance to smart speakers as a device class, all of this
functionality—an always-on microphone listening, waiting to be called upon,
recording your command and sending it to the cloud for processing—already
exists in modern smartphones as well.
SEE: Alexa Skills: A guide for business pros (free
PDF)<https://www.techrepublic.com/resource-library/whitepapers/alexa-skills-a-guide-for-business-pros-free-pdf/>
(TechRepublic)
Google is pushing this voice recognition from the cloud onto the edge, with the
new Google Assistant unveiled at I/O
2019<https://www.cnet.com/features/google-assistant-is-10x-faster-and-knows-where-your-mom-lives/>,
that uses a compacted machine learning library that the company claims is
built from 100 GB of data to less than half a gigabyte, with CNET noting that
"the souped-up digital helper requires hefty computing power for a phone, so it
will only be available on high-end devices. Google will debut the product on
the next premium version of its flagship Pixel
phone<https://www.cnet.com/news/pixel-4-4-xl-rumors-price-specs-leaks-features-everything-else-dual-camera-android-q/>,
expected in the fall."
For developers, Google is expanding their Edge ML
capabilities<https://www.zdnet.com/article/google-expands-ml-kit-capabilities-for-building-machine-learning-into-mobile-apps/>,
with betas of the On-device Translation API, an Object Detection & Tracking
API, and AutoML Vision Edge unveiled at I/O
2019<https://www.cnet.com/news/google-io-from-android-to-assistant-heres-what-to-expect/>.
The technology that powers the next-generation Google Assistant is not (yet)
deployable for developers' projects, however.
Options for third-party developers
That does not mean that third-party developers cannot take advantage of
on-device voice recognition, however. Snips<https://snips.ai/>, a French
software firm, makes the Snips platform freely available for non-commercial
use, and requires an order of magnitude less in terms of processing power, as
it is capable of running on a Raspberry Pi
3<https://www.techrepublic.com/article/raspberry-pi-no-longer-the-fastest-35-computers-but-still-the-best/>.
The Snips platform itself does not require an internet connection to operate,
though integrations that require internet access—obviously—do.
"The main differentiator of the Snips platform is that it focuses on all the
components required to build high quality voice interfaces: Wake word
detection, Speech Recognition, and Natural Language Understanding," Snips CTO
Joseph Dureau told TechRepublic. "In contrast, none of these voice processing
algorithms are included in the Google ML Kit," adding that "Our data generation
solutions makes it possible to generate large volumes of diverse and
high-quality training data, for any voice interface use case. It enables
developers to train their assistants with very high performance before their
actual launch, helping them to overcome the cold start problem."
Snips boasts a community of over 25,000 developers, and the platform presently
supports English, French, Japanese, Spanish, Italian, and Portuguese.
The potential for developers to utilize this technology in their applications
could assuage some of the concerns—founded or otherwise—of those reluctant to
adopt voice-activated smart assistants.
For more, check out the 5 biggest IoT security failures of
2018<https://www.techrepublic.com/article/5-biggest-iot-security-failures-of-2018/>,
and why data security is now a top concern for IT
leaders<https://www.techrepublic.com/article/why-data-security-is-now-a-top-concern-for-it-leaders/>.
[https://tr4.cbsistatic.com/fly/bundles/techrepubliccss/images/article-NLSthumb.jpg]
Tech News You Can Use Newsletter
We deliver the top business tech news stories about the companies, the people,
and the products revolutionizing the planet. Delivered Daily
Sign up today Sign up today
Also see
[voiceistock-868172652andrey-suslov.jpg]
Getty Images/iStockphoto
https://www.techrepublic.com/article/on-device-speech-recognition-may-make-smart-assistants-more-appealing/#ftag=RSS56d97e7
David Goldfield
Assistive Technology Specialist
Feel free to visit my Web site
WWW.DavidGoldfield.info<http://WWW.DavidGoldfield.info>