CLOSINGS: View Closings

Watch out, Alexa. Artificial voices are starting to sound just like humans

It could be any ad on YouTube: A blonde model playfully puts her hand in front of the camera lens, dons white sunglasses and flashes a grin. In the backgroun...

Posted: Mar 7, 2019 12:00 PM

It could be any ad on YouTube: A blonde model playfully puts her hand in front of the camera lens, dons white sunglasses and flashes a grin. In the background, hip-hop music plays while an unmistakably female voice says, "Fashion changes, but style lasts forever."

The ad — part of a demo reel on YouTube created by a new startup called WellSaid Labs — is short and slick. But something is a bit different. While the model you see is a human, the background voice you hear only sounds like one.

The Seattle-based company is using voice actors and artificial intelligence to create synthetic voices that sound a heck of a lot like people. The company claims the text-to-speech software it has been working on for the past year can produce audio that sounds more human-like than other synthetic voices. The reason, according to the company, is that it is not tightly controlling different variables of speech like speed, pronunciation, and volume when training its voice model.

"The voice we're trying to create here is super expressive and lifelike in its final result," WellSaid Labs CEO Matt Hocking told CNN Business.

Computerized voices seem to be everywhere these days, offering news from a smart speaker in your living room or giving you turn-by-turn directions in the car. Yet Alexa, Siri, Google Assistant and others that you're likely to hear from still tend to speak in stilted, robot-tinged voices. (A notable exception, Google Duplex, can call some businesses to make reservations with an impressively human-sounding AI-enabled voice; Google is making it increasingly available, but you'd have to be on the receiving end of a phone call — at a restaurant, for instance — to hear it).

WellSaid Labs isn't planning to take over the voice-assistant market, though. Rather, Hocking said, it hopes to sell the voices to companies that want to use them in advertising, marketing and e-learning courses.

The company says it's building a number of human-like voices that customers will be able to use, and hopes to work with voice actors to create a different data sets that can be used to create all kinds of artificial voices.

You've probably heard of stock photos; you might think of this as stock voices.

To make the woman's voice in the faux ads, WellSaid Labs first had a voice actor read articles from Wikipedia. These recordings formed a data set that it used to train an artificial neural network — a computing system whose structure is modeled loosely after neurons in a brain.

Another online demo shows how similar the AI-generated voices can sound to the actors, with audio alternating between two almost indistinguishable voices — one the human voice-over actor, one her AI-generated voice — that sound like a middle-aged woman. You might occasionally notice some differences, but they're slight; the emphasis you'd expect might be off by just a bit in a word, for instance.

The startup said it doesn't need to pre-process or annotate text given to the software for it to be able to do things like emphasize words in a natural-sounding way — something that is difficult for an artificial voice to do without help (though companies such as Google have been working on it). And if you fed the same text to its text-to-speech generator twice, you'd get different results.

It takes about four seconds to render a line of text right now, said chief technology officer Michael Petrochuk. The model isn't built to interpret long pieces of text, though: it can be used to speak several sentences, but the text of an entire CNN Business article, for example, would need to be cut into pieces before it could be analyzed and spoken by a WellSaid Labs voice.

It's hard to make a synthetic voice sound consistently good. Alan Black, a professor of language technologies at Carnegie Mellon University, said that the ones we're familiar with, such as Amazon's Alexa, are robotic sounding because it's tricky to make it sound natural in all situations. It's difficult, he said, to give the right amount of information to a speech synthesizer so it can respond with the right amount of feeling.

"We don't have a little knob on our synthesizer to say 'Do feeling 87%,'" he said.

He listened to some of WellSaid Labs' demo voices, and thought they sounded "pretty good."

But if artificial voices sound close to — or indistinguishable from — humans, should listeners be clued in that they're not listening to a real person talk? After Google demonstrated Duplex in 2018 with a call that its human-sounding AI made to a Bay Area restaurant, the tech company was criticized for not having the AI disclose what it was.

Black doesn't think that disclosure is necessary, at least in the context of ads.

"I think that in general most people are relatively aware that what they see in video and audio is in some sense processed," he said. "They know that when they're watching 'The Lord of The Rings' there really aren't a lot of orcs in New Zealand appearing in the movie."

Indiana Coronavirus Cases

Data is updated nightly.

Cases: 1462456

Reported Deaths: 20308
CountyCasesDeaths
Marion2005922494
Lake992001456
Allen903391005
Hamilton70705539
St. Joseph63078746
Elkhart48098622
Vanderburgh46217523
Tippecanoe42115330
Johnson37119516
Hendricks35078455
Porter33900460
Madison28036530
Clark25186321
Vigo24768341
LaPorte22894307
Monroe22201243
Howard21344372
Delaware20937363
Hancock18289217
Kosciusko17513199
Bartholomew17399212
Warrick16060212
Wayne15757296
Floyd15399252
Grant14898293
Morgan13934230
Boone13172136
Noble11421140
Dearborn11355112
Henry11312201
Shelby11231150
Marshall11041166
Dubois10782152
Jackson10174104
DeKalb9944128
Cass9942142
Lawrence9914219
Huntington9823139
Gibson9131125
Montgomery9005140
Knox8762124
Harrison8718111
Whitley844771
Steuben8340102
Jasper8069113
Putnam795197
Clinton792994
Miami7914133
Wabash7598138
Jefferson7551124
Ripley6993111
Adams6508101
Scott629086
Daviess6266127
White602379
Greene5913111
Clay587173
Wells5814120
Decatur5754118
Jennings572276
Fayette5657121
Posey529146
LaGrange512996
Randolph4925128
Washington482067
Owen480398
Fountain463579
Spencer438156
Starke434086
Sullivan432164
Fulton426790
Orange412682
Jay403964
Rush395736
Carroll371349
Franklin369850
Perry362155
Vermillion345062
Pike308945
Tipton307974
Parke305038
Pulaski266973
Blackford266755
Newton228359
Brown222654
Benton213321
Crawford211231
Switzerland189414
Martin181921
Warren169520
Union163619
Ohio119516
Unassigned0742

Ohio Coronavirus Cases

Data is updated nightly.

Cases: 2403645

Reported Deaths: 30922
CountyCasesDeaths
Franklin2596932036
Cuyahoga2572672998
Hamilton1666711699
Montgomery1103831586
Summit1066861382
Lucas895171149
Butler78647924
Stark747301383
Lorain62885783
Warren49934468
Mahoning49735909
Lake46850586
Clermont43541428
Delaware38876210
Trumbull38576748
Medina37611416
Licking36901401
Fairfield33848331
Greene32124416
Portage31381356
Clark30277440
Richland28251420
Wood27660289
Allen24372392
Miami22806389
Muskingum22298244
Columbiana22095399
Wayne21275354
Tuscarawas18847423
Erie18041221
Ashtabula17932338
Marion17503231
Scioto16553203
Ross16163249
Pickaway15536173
Hancock15251227
Geauga15244221
Lawrence13847186
Huron13399182
Union1329683
Belmont13255247
Jefferson12864257
Sandusky12770197
Athens11949106
Knox11511195
Seneca11454200
Ashland10795174
Darke10673196
Washington10564168
Auglaize10152141
Crawford9854175
Shelby9699155
Brown9400140
Fulton9235148
Guernsey9109115
Defiance9057134
Highland9035143
Logan8955141
Clinton8719121
Mercer8640111
Madison8568104
Preble8002160
Williams7848135
Putnam7731135
Ottawa7629120
Champaign7556112
Jackson7383114
Perry714598
Coshocton7043136
Morrow694580
Fayette662287
Hardin6219125
Pike617086
Gallia594989
Adams5779124
Van Wert5779120
Henry565592
Hocking5521103
Carroll4828100
Wyandot482289
Holmes4747161
Paulding401163
Meigs375071
Monroe299368
Noble279851
Harrison279461
Morgan276848
Vinton239845
Unassigned08
Fort Wayne
Cloudy
32° wxIcon
Hi: 36° Lo: 24°
Feels Like: 23°
Angola
Cloudy
32° wxIcon
Hi: 34° Lo: 23°
Feels Like: 23°
Huntington
Cloudy
35° wxIcon
Hi: 38° Lo: 23°
Feels Like: 28°
Decatur
Cloudy
32° wxIcon
Hi: 37° Lo: 24°
Feels Like: 23°
Van Wert
Cloudy
33° wxIcon
Hi: 36° Lo: 24°
Feels Like: 23°
A gusty south wind pushes temperatures above the freezing mark Tuesday afternoon.
WFFT Radar
WFFT Temperatures
WFFT National

Community Events