How Alexa knows the difference between a breaking window and a wine glass

For Amazon, getting Alexa's new security-guard feature to work meant literally breaking a lot of windows....

Posted: Jan 15, 2019 5:47 PM
Updated: Jan 15, 2019 5:47 PM

For Amazon, getting Alexa's new security-guard feature to work meant literally breaking a lot of windows.

In December, the company started inviting Amazon Echo users to try out Alexa Guard, a new setting that turns the smart speakers into home security devices. It listens for suspicious sounds when you're away and sends a smartphone alert if it detects, say, a window breaking and a possible break in.

Alcoholic beverages

Amazon.com Inc

Artificial intelligence

Beverages

Business and industry sectors

Business, economy and trade

Companies

Computer science and information technology

Consumer products

Food and drink

Kinds of foods and beverages

Technology

Voice and virtual assistants

Wine

According to Prem Natarajan, vice president of Alexa's AI division, Amazon employees had to destroy different types of glass, such as window glass, wine glasses and drinking glasses, with tools like baseballs or hammers to train the technology.

Considering most of us have all kinds of glass things in our homes, it was important for Alexa to learn the difference between a cat knocking over a wine glass and a burglar smashing a living-room window.

"You don't want [Alexa] to respond to any glass breaking," Natarajan told CNN Business.

Machine learning -- a type of artificial intelligence that learns from data and improves over time -- underpins Alexa's ability to respond to a trigger word and command.

Alexa Guard is activated by the spoken command, "Alexa, I'm leaving," which is picked up by the Echo's built-in microphones. In addition to detecting broken glass, the feature lets the Echo keep an ear out for a smoke or carbon-monoxide detector blaring, and can turn on smart lights to make it look like someone is home.

Natarajan said Amazon first tried to train Alexa Guard to recognize window-smashing sounds with audio of glass breaking from movies. But that proved unsuccessful when the software was tasked with sorting through real-world sounds.

However, breaking real windows and dropping glass from different heights allowed Amazon to collect data that showed differences in acoustic characteristics for various objects and scenarios. This data was then used to train a machine-learning algorithm to recognize the right kind of noise.

Alexa Guard is a way for Amazon to differentiate Alexa from Google's Assistant, Apple's Siri, and others in the rapidly growing market for voice assistants. Plenty of home-security systems can detect breaking glass, but they typically require a separate sensor and may only work over a small area.

According to MIT spoken language systems group leader Jim Glass -- yes, that's his real last name -- Amazon should be able to train Alexa to recognize anything that average human can learn to discern with their ears.

"They can use it to try and pick up the sound of a breaking window; maybe they can train it to try and learn when your bathtub is overflowing," he suggested.

But perhaps the team will need to stock up on bathtubs first.

Minnesota Coronavirus Cases

Data is updated nightly.

Confirmed Cases: 22464

Reported Deaths: 942
CountyConfirmedDeaths
Hennepin7540565
Ramsey2610103
Stearns198412
Nobles14883
Anoka126259
Dakota118244
Olmsted57510
Washington56230
Kandiyohi4751
Rice4112
Clay40625
Scott3792
Todd2960
Wright2691
Sherburne2192
Mower2161
Carver1852
Benton1692
Steele1480
Martin1265
Blue Earth1221
St. Louis11513
Freeborn970
Pine850
Winona7815
Nicollet747
Carlton730
Cottonwood650
Otter Tail620
Unassigned6110
Goodhue603
Watonwan590
Polk592
Crow Wing571
Itasca537
Chisago501
Dodge460
Chippewa441
Meeker440
Le Sueur431
Morrison400
Douglas390
Jackson390
Becker370
Murray360
Lyon360
Isanti330
McLeod290
Waseca240
Rock210
Swift170
Pennington170
Mille Lacs171
Fillmore171
Wabasha170
Brown142
Faribault130
Beltrami130
Sibley130
Cass122
Norman110
Wilkin113
Kanabec111
Pipestone100
Marshall90
Pope80
Wadena80
Aitkin70
Koochiching70
Yellow Medicine60
Lincoln50
Renville50
Mahnomen51
Red Lake40
Traverse30
Big Stone30
Clearwater30
Redwood30
Grant30
Lac qui Parle30
Houston20
Lake10
Hubbard10
Roseau10
Kittson10

Iowa Coronavirus Cases

Data is updated nightly.

Confirmed Cases: 18342

Reported Deaths: 496
CountyConfirmedDeaths
Polk3876115
Woodbury265831
Black Hawk171343
Linn93876
Marshall87815
Dallas87317
Buena Vista6820
Johnson6058
Muscatine54741
Wapello5384
Crawford4882
Tama40026
Scott34610
Louisa33610
Dubuque33016
Jasper25716
Pottawattamie2277
Sioux2100
Washington1858
Wright1240
Allamakee1194
Plymouth1191
Warren1140
Story961
Poweshiek888
Mahaska888
Bremer676
Henry671
Clinton601
Des Moines581
Boone560
Taylor480
Cedar461
Guthrie443
Clarke400
Benton391
Jones360
Iowa360
Monroe354
Shelby350
Clayton313
Buchanan310
Osceola310
Marion300
Webster291
Hamilton280
Madison261
Fayette260
Monona240
Lee230
Cherokee230
Winneshiek230
Cerro Gordo221
Davis200
Jefferson190
Harrison190
Lyon190
Grundy190
Floyd181
Sac170
Mills160
Hardin150
Butler150
Delaware150
Humboldt140
Ida140
Keokuk140
Hancock140
Appanoose133
Jackson130
Dickinson130
Clay130
Greene130
Howard120
Audubon121
Winnebago110
Cass110
Page100
Van Buren90
Franklin90
Carroll90
Pocahontas90
Chickasaw80
Emmet80
Unassigned80
Kossuth80
Adair70
Adams70
Lucas70
Union60
Montgomery60
Mitchell50
Ringgold40
Fremont40
Palo Alto30
Worth30
Calhoun20
Decatur10
Wayne10
Rochester
Scattered Clouds
66° wxIcon
Hi: 74° Lo: 50°
Feels Like: 66°
Mason City
Few Clouds
71° wxIcon
Hi: 75° Lo: 51°
Feels Like: 71°
Albert Lea
Clear
73° wxIcon
Hi: 75° Lo: 51°
Feels Like: 73°
Austin
Clear
72° wxIcon
Hi: 77° Lo: 52°
Feels Like: 72°
Charles City
Clear
68° wxIcon
Hi: 75° Lo: 50°
Feels Like: 68°
Lingering showers Thursday AM will turn to sunshine by the afternoon
KIMT Radar
KIMT Eye in the sky

Community Events