Google Demos Duplex



For one minute and ten seconds on Tuesday, I worked in a trendy hummus shop and took a reservation from a guy who punctuated his sentences with “awesome” and “um.”

“Hi, I’m calling to make a reservation,” the caller said, sounding a lot like a stereotypical California surferThen he came clean: “I’m Google’s automated booking service, so I’ll record the call. Um, can I book a table for Saturday?”

The guy was Google Duplex, the AI-assisted assistant that made a stir in May when CEO Sundar Pichai unveiled it at its Google I/O developer conferenceThat demo, shown in a slick video, was so impressive that some people said it had to be fake.

Not so, says Google, which invited clusters of reporters to Oren’s Hummus Shop near its campus in Mountain View, for a hands-on demonstrationEach of us got to field an automated call and test the system’s limits.

但是,关于好奇的录音在5月初的I / O舞台上演出:

Scott Huffman, the VP of engineering for Google Assistant, conceded that the demo at I/O in May “maybe made it look a little too polished.” That’s because Pichai tends to focus on Google’s grand visions for the future, Huffman said.

Ron Amadeo,为Ars Technica写作

Unfortunately, Google would not let us record the live interactions this week, but it did provide a video we’ve embedded belowThe robo call in the video is, honestly, perfectly representative of what we experiencedBut to allay some of the skepticism out there, let’s first outline the specifics of how this demo was set up along with what worked and what didn’t[...]

During the demonstration period, things went much more according to planOver the course of the event, we heard several calls, start to finish, handled over a live phone systemTo start, a Google rep went around the room and took reservation requirements from the group, things like “What time should the reservation be for?” or “How many people?” Our requirements were punched into a computer, and the phone soon rangJournalists — err, restaurant employees — could dictate the direction of the call however they so chooseSome put in an effort to confuse Duplex and throw it some curveballs, but this AI worked flawlessly within the very limited scope of a restaurant reservation.

这是视频谷歌提供了这确实是一个令人印象深刻的近似人类说话事实上,有一点突出的是女性手机上Google智能助理的人工声音之间的区别 - 没有,不是啊,机器人精确 - 以及电话中双工的明显非机器人声音。

关于实际用户的实际部署,一些非特定数量的“受信任的测试人员”很快就可以访问Duplex,但仅用于询问餐厅营业时间,进行预订 - 理发预约功能除了“以后”之外没有交付日期,并且没有向媒体展示。

Dieter Bohn, writing at The Verge

If you’re hoping that means you’ll be able to try it yourself, sorry: Google is starting with “a set of trusted tester users,” according to Nick Fox, VP of product and design for the Google AssistantIt will also be limited to businesses that Google has partnered with rather than any old restaurant.

换句话说,推出将分阶段进行First up will be calls about holiday hours, then restaurant reservations will come later this summer, and then finally hair cut appointments will be lastThose are the only three domains that Google has trained Duplex on.


The more natural, human-sounding voice wasn’t there in the very first prototypes that Google built (amusingly, they worked by setting a literal handset on the speaker on a laptop)According to VP of engineering for the Google Assistant Scott Huffman, “It didn’t work...we got a lot of hangups, we got a lot of incompletion of the taskPeople didn’t deal well with how unnatural it sounded.”

Part of making it sound natural enough to not trigger an aural sense of the uncanny valley was adding those ums and ahs, which Huffman identified as “speech disfluencies.” He emphasized that they weren’t there to trick anybody, but because those vocal tics “play a key part in progressing a conversation between humans.” He says it came from a well-known branch of linguistics called “pragmatics,” which encompasses all the non-word communications that happen in human speech: the ums, the ahs, the hand gestures, etc.


The fact that they started getting fewer hangups when they added these natural-sounding imperfections makes sense但说他们没有使用这些嗯是不诚实的啊,欺骗这个人认为它是一个人这正是他们正在做的事情The problem is,淋水听起来很狡猾在这种情况下,我不确定是不是这只是让通话中的人更舒服我们在所有技术中使用“技巧”举一个例子,动态影像实际上并没有移动 - 它们只是一系列静止的图像,它们的播放速度足以让我们的眼睛看到动作。

无论是否有Duplex的参与,餐厅都会接到预订电话(Duplex doesn’t make phone calls for restaurants that support online booking through OpenTable — at least not if the device user has an OpenTable account.) Based on these examples, Duplex doesn’t seem to waste the restaurant’s time — the phone calls take about the same time as they would if you, the human, made the call yourself因此,当Duplex打电话时,餐厅和接听电话的员工都没有丢失任何东西,无论他们是否意识到他们正在与AI交谈没有人会受到欺骗,例如玩在线扑克的机器人。


Lauren Goode,在连线写作

然后我问这个小组是否有过敏症“OK, so, 7:30,” the bot said“No, I can fit you in at 7:45,” I said. The bot was confused“7:30,”它又说了一遍I also asked whether they would need a high chair for any small childrenAnother voice eventually interjected, and completed the reservation.

I hung up the phone feeling somewhat triumphant; my stint in college as a host at a brew house had paid off, and I had asked a series of questions that a bot, even a good one, couldn’t answer. It was a win for humans“In that case, the operator that completed the call — that wasn’t a human, right?” I asked Nygaard不,她说那是接管电话的人I was stunned; in the end, I was still a human who couldn’t differentiate between a voice powered by silicon and one born of flesh and blood.


我仍然认为整个事情就像一个技术演示(类似人类的演讲),而不是产品谷歌本周声称Duplex目前在预订时成功完成了5次中的4次人类操作员的干预对于演示而言,这是一个很好的击球平均值,但对于谷歌规模的运输产品来说却难以为继由于失败率为20%,谷歌需要一整天的人力资源运营商,以支持他们没有从中赚钱的功能。我怀疑这将是一个扩展到广泛使用的产品,如果是,它可能是年份远谷歌说了很多到Ars Technica

“We’re actually quite a long way from launch, that’s the key thing to understand,” Fox explained at the meeting“This is super-early technology, somewhere between technology demo and productWe’re talking about this way earlier than we typically talk about products.”

现在它感觉像是一个搜索产品的功能,但他们把它作为I / O的迫近产品,因为它做了一个惊人的演示(It remains the only thing announced at I/O that anyone is talking about.) If what Google really wanted was just for Google Assistant to be able to make restaurant reservations, they’d be better off building an OpenTable competitor and giving it away to all these small businesses that don’t yet offer online reservations我不会为Duplex屏住呼吸,允许任何人在任何机构预订。