Rana el Kaliouby: This app knows how you feel — from the look on your face

137,190 views ・ 2015-06-15

TED


请双击下面的英文字幕来播放视频。

翻译人员: Li Li 校对人员: Huazhe Xie
00:12
Our emotions influence every aspect of our lives,
0
12556
4017
我们的情感影响着我们生活的方方面面,
00:16
from our health and how we learn, to how we do business and make decisions,
1
16573
3576
它影响我们的健康,影响我们如何学习、做生意以及做决定,
00:20
big ones and small.
2
20149
1773
影响着大大小小各各方面。
00:22
Our emotions also influence how we connect with one another.
3
22672
3490
我们的情感还影响着我们与他人的联系的方式。
00:27
We've evolved to live in a world like this,
4
27132
3976
我们进化成可以生活在现在这样的世界,
00:31
but instead, we're living more and more of our lives like this --
5
31108
4319
然而我们却越来越生活成这样子——
00:35
this is the text message from my daughter last night --
6
35427
3134
这是我女儿昨晚给我发的短信——
00:38
in a world that's devoid of emotion.
7
38561
2740
这是个缺乏情感的世界。
00:41
So I'm on a mission to change that.
8
41301
1951
所以我现在正致力于改变那种情况。
00:43
I want to bring emotions back into our digital experiences.
9
43252
4091
我想把情感带回到我们的数字体验中来。
00:48
I started on this path 15 years ago.
10
48223
3077
15年前我就开始走上了这条道路。
00:51
I was a computer scientist in Egypt,
11
51300
2066
那时我是一个生活在埃及的计算机科学家,
00:53
and I had just gotten accepted to a Ph.D. program at Cambridge University.
12
53366
4505
并且刚刚接受了剑桥大学的博士学位项目。
00:57
So I did something quite unusual
13
57871
2113
我做了一件对于一个年轻的
00:59
for a young newlywed Muslim Egyptian wife:
14
59984
4225
埃及穆斯林新婚妻子来说非常不寻常的事情:
01:05
With the support of my husband, who had to stay in Egypt,
15
65599
2999
我的丈夫不能离开埃及,但在他的支持下,
01:08
I packed my bags and I moved to England.
16
68598
3018
我独自收拾行李搬到英国去了。
01:11
At Cambridge, thousands of miles away from home,
17
71616
3228
在离家数千里之外的剑桥,
01:14
I realized I was spending more hours with my laptop
18
74844
3413
我意识到我花在笔记本电脑上的时间
01:18
than I did with any other human.
19
78257
2229
要多于我与其他人相处的时间。
01:20
Yet despite this intimacy, my laptop had absolutely no idea how I was feeling.
20
80486
4853
然而尽管我和电脑如此亲密,电脑却对我的感受毫无所知。
01:25
It had no idea if I was happy,
21
85339
3211
它根本不知道我是快乐,
01:28
having a bad day, or stressed, confused,
22
88550
2988
还是经历着糟糕的一天,或者是感到有压力、困惑,
01:31
and so that got frustrating.
23
91538
2922
这就很让人不爽。
01:35
Even worse, as I communicated online with my family back home,
24
95600
5231
而且更糟的是,当我回家后在线跟家人聊天时,
01:41
I felt that all my emotions disappeared in cyberspace.
25
101421
3282
我觉得我所有的情感都在网络空间中消失了。
01:44
I was homesick, I was lonely, and on some days I was actually crying,
26
104703
5155
我想家,我感到孤独,而且有些日子我真的哭了,
01:49
but all I had to communicate these emotions was this.
27
109858
4928
而我也仅仅只能用这个表情来表达我的情感。
01:54
(Laughter)
28
114786
2020
(笑声)
01:56
Today's technology has lots of I.Q., but no E.Q.;
29
116806
4974
现今有很多技术具有智商,但是还没有具有情商的,
02:01
lots of cognitive intelligence, but no emotional intelligence.
30
121780
3176
很多技术具有认知性智能,但还没有具有情绪性智能的。
02:04
So that got me thinking,
31
124956
2197
这让我想到,
02:07
what if our technology could sense our emotions?
32
127153
3624
如果我们的技术可以识别我们的情绪将会怎样?
02:10
What if our devices could sense how we felt and reacted accordingly,
33
130777
4076
如果我们的设备能识别我们的感受并做出相应的反应,
02:14
just the way an emotionally intelligent friend would?
34
134853
3013
就像情商高的朋友所做的那样将会怎样?
02:18
Those questions led me and my team
35
138666
3564
这些问题引导着我和我的团队
02:22
to create technologies that can read and respond to our emotions,
36
142230
4377
去创造可以阅读我们的情绪并做出反应的技术,
02:26
and our starting point was the human face.
37
146607
3090
我们的起点是人脸。
02:30
So our human face happens to be one of the most powerful channels
38
150577
3173
人脸是交流的最强大的渠道之一,
02:33
that we all use to communicate social and emotional states,
39
153750
4016
我们所有人都用它来表达社会和情绪状态,
02:37
everything from enjoyment, surprise,
40
157766
3010
从喜悦、惊讶
02:40
empathy and curiosity.
41
160776
4203
到同情、好奇等等。
02:44
In emotion science, we call each facial muscle movement an action unit.
42
164979
4928
在情感科学中,我们将每一个面肌运动称为一个动作单元。
02:49
So for example, action unit 12,
43
169907
2925
例如,动作单元12,
02:52
it's not a Hollywood blockbuster,
44
172832
2038
这不是好莱坞大片,
02:54
it is actually a lip corner pull, which is the main component of a smile.
45
174870
3442
这就是简单的嘴角上扬,它是微笑的主要构成。
02:58
Try it everybody. Let's get some smiles going on.
46
178312
2988
大家都试一下。让我们都微笑起来。
03:01
Another example is action unit 4. It's the brow furrow.
47
181300
2654
另一个例子是动作单元4。它是眉间纹。
03:03
It's when you draw your eyebrows together
48
183954
2238
当你将眉毛拧到一起的时候
03:06
and you create all these textures and wrinkles.
49
186192
2267
你就创造出了这些纹理和皱纹。
03:08
We don't like them, but it's a strong indicator of a negative emotion.
50
188459
4295
我们不喜欢它,但它是一个非常强的负面情绪指示器。
03:12
So we have about 45 of these action units,
51
192754
2206
我们大概有45个这样的单元,
03:14
and they combine to express hundreds of emotions.
52
194960
3390
它们的组合可以表达上百种情绪。
03:18
Teaching a computer to read these facial emotions is hard,
53
198350
3901
教会电脑去读取这些面部情绪很难,
03:22
because these action units, they can be fast, they're subtle,
54
202251
2972
因为这些动作单元行动很微妙,而且稍纵即逝,
03:25
and they combine in many different ways.
55
205223
2554
而且它们有很多的组合方式。
03:27
So take, for example, the smile and the smirk.
56
207777
3738
例如,微笑和假笑。
03:31
They look somewhat similar, but they mean very different things.
57
211515
3753
它们看起来有几分相似,但意味却是天差地别。
03:35
(Laughter)
58
215268
1718
(笑声)
03:36
So the smile is positive,
59
216986
3004
微笑是正面的,
03:39
a smirk is often negative.
60
219990
1270
假笑常常是负面的。
03:41
Sometimes a smirk can make you become famous.
61
221260
3876
有时一个假笑可以让你出名。
03:45
But seriously, it's important for a computer to be able
62
225136
2824
但是严肃地讲,让电脑能够
03:47
to tell the difference between the two expressions.
63
227960
2855
描述这两种表情的区别是很重要的。
03:50
So how do we do that?
64
230815
1812
那我们是如何做的呢?
03:52
We give our algorithms
65
232627
1787
我们给我们的算法
03:54
tens of thousands of examples of people we know to be smiling,
66
234414
4110
成千上万的不同种族、年龄和性别的人们
03:58
from different ethnicities, ages, genders,
67
238524
3065
正在微笑的例子,
04:01
and we do the same for smirks.
68
241589
2811
然后我们也用同样的方法研究假笑。
04:04
And then, using deep learning,
69
244400
1554
然后使用深度学习,
04:05
the algorithm looks for all these textures and wrinkles
70
245954
2856
算法可以观察我们脸上的所有这些纹理和皱纹
04:08
and shape changes on our face,
71
248810
2580
以及形状变化,
04:11
and basically learns that all smiles have common characteristics,
72
251390
3202
并且基本上得知所有的微笑都有共同特性,
04:14
all smirks have subtly different characteristics.
73
254592
3181
而所有的假笑都有些微的不同特性。
04:17
And the next time it sees a new face,
74
257773
2368
然后下一次当它看到一个新面孔时,
04:20
it essentially learns that
75
260141
2299
它就基本上能知道
04:22
this face has the same characteristics of a smile,
76
262440
3033
这张面孔上有和微笑相同的特性,
04:25
and it says, "Aha, I recognize this. This is a smile expression."
77
265473
4278
然后它就会说:“啊哈,我知道了,这是一个微笑的表情。”
04:30
So the best way to demonstrate how this technology works
78
270381
2800
所以展示这种技术如何工作的最好方式
04:33
is to try a live demo,
79
273181
2136
是来一个现场演示,
04:35
so I need a volunteer, preferably somebody with a face.
80
275317
3913
所以我需要一位志愿者,最好是个“有脸”的人。
04:39
(Laughter)
81
279230
2334
(笑声)
04:41
Cloe's going to be our volunteer today.
82
281564
2771
克洛将成为我们今天的志愿者。
04:45
So over the past five years, we've moved from being a research project at MIT
83
285325
4458
在过去的5年间,我们从只是麻省理工学院的一个研究项目
04:49
to a company,
84
289783
1156
到成立一个公司,
04:50
where my team has worked really hard to make this technology work,
85
290939
3192
在公司里我的团队非常非常努力地工作以使这项技术成功,
04:54
as we like to say, in the wild.
86
294131
2409
就像我们说的那样,我们在荒野里生存。
04:56
And we've also shrunk it so that the core emotion engine
87
296540
2670
我们还将它缩小了,这样的话这个核心情绪引擎
04:59
works on any mobile device with a camera, like this iPad.
88
299210
3320
就能在一个带摄像头的移动设备上运行,比如这个iPad。
05:02
So let's give this a try.
89
302530
2786
让我们来试一试。
05:06
As you can see, the algorithm has essentially found Cloe's face,
90
306756
3924
正如你们看到的,此算法基本上找到了克洛的脸,
05:10
so it's this white bounding box,
91
310680
1692
就是这个白色的边界框,
05:12
and it's tracking the main feature points on her face,
92
312372
2571
它在跟踪她脸上的主要特征点,
05:14
so her eyebrows, her eyes, her mouth and her nose.
93
314943
2856
她的眉毛、眼睛、嘴巴和鼻子。
05:17
The question is, can it recognize her expression?
94
317799
2987
问题是,它能识别她的表情吗?
05:20
So we're going to test the machine.
95
320786
1671
那么我们测试一下这台机器。
05:22
So first of all, give me your poker face. Yep, awesome. (Laughter)
96
322457
4186
首先,做一个面无表情的样子。嗯,好极了。(笑声)
05:26
And then as she smiles, this is a genuine smile, it's great.
97
326643
2813
然后当她微笑时,这是一个真诚的微笑,很好。
05:29
So you can see the green bar go up as she smiles.
98
329456
2300
大家可以看到当她微笑时这些绿条增长了。
05:31
Now that was a big smile.
99
331756
1222
这是一个大大的微笑。
05:32
Can you try a subtle smile to see if the computer can recognize?
100
332978
3043
你能试着轻轻微笑一下,看看电脑能否识别出来吗?
05:36
It does recognize subtle smiles as well.
101
336021
2331
它确实也能识别轻轻的微笑。
05:38
We've worked really hard to make that happen.
102
338352
2125
我们付出了很多的努力才使它能够做到这些。
05:40
And then eyebrow raised, indicator of surprise.
103
340477
2962
眉毛上扬,是惊喜的标志。
05:43
Brow furrow, which is an indicator of confusion.
104
343439
4249
眉间的皱纹,是困惑的标志。
05:47
Frown. Yes, perfect.
105
347688
4007
皱眉。嗯,很完美。
05:51
So these are all the different action units. There's many more of them.
106
351695
3493
这些都是不同的行动单元。还有很多这样的行动单元。
05:55
This is just a slimmed-down demo.
107
355188
2032
这只是一个小型的演示。
05:57
But we call each reading an emotion data point,
108
357220
3148
我们称每一次读取为一个情感数据点,
06:00
and then they can fire together to portray different emotions.
109
360368
2969
然后它们可以组合在一起来描绘不同的情绪。
06:03
So on the right side of the demo -- look like you're happy.
110
363337
4653
因此在演示的右边,你看起来很开心。
06:07
So that's joy. Joy fires up.
111
367990
1454
那表示快乐,快乐就被启动了。
06:09
And then give me a disgust face.
112
369444
1927
再做一个厌恶的表情。
06:11
Try to remember what it was like when Zayn left One Direction.
113
371371
4272
试着回想一下当泽恩离开单向乐队时的情景。
06:15
(Laughter)
114
375643
1510
(笑声)
06:17
Yeah, wrinkle your nose. Awesome.
115
377153
4342
是的,皱一下鼻。很好。
06:21
And the valence is actually quite negative, so you must have been a big fan.
116
381495
3731
而“抗体效价”一项也呈现负值,因此你一定是他们的铁杆粉丝。
06:25
So valence is how positive or negative an experience is,
117
385226
2700
抗体效价是用来描述一种体验的积极或消极程度的,
06:27
and engagement is how expressive she is as well.
118
387926
2786
而“参与度”是用来描述她的表现力的。
06:30
So imagine if Cloe had access to this real-time emotion stream,
119
390712
3414
所以大家可以想象一下如果克洛能够使用这种实时的情感流,
06:34
and she could share it with anybody she wanted to.
120
394126
2809
并且能分享给任何她想分享的人的情景。
06:36
Thank you.
121
396935
2923
谢谢。
06:39
(Applause)
122
399858
4621
(掌声)
06:45
So, so far, we have amassed 12 billion of these emotion data points.
123
405749
5270
迄今为止,我们已经积累了120亿这种情感数据点。
06:51
It's the largest emotion database in the world.
124
411019
2611
这是世界上最大的情感数据库。
06:53
We've collected it from 2.9 million face videos,
125
413630
2963
我们是从两百九十万个面部视频中去收集的,
06:56
people who have agreed to share their emotions with us,
126
416593
2600
这些视频来自那些同意将他们的情感与我们一起分享的人们,
06:59
and from 75 countries around the world.
127
419193
3205
并且这些人们来自全世界75个国家。
07:02
It's growing every day.
128
422398
1715
它每天都在发展。
07:04
It blows my mind away
129
424603
2067
它发散了我的思维:
07:06
that we can now quantify something as personal as our emotions,
130
426670
3195
原来我们可以将情绪这么个性化的东西进行量化,
07:09
and we can do it at this scale.
131
429865
2235
并且是在这样的规模下去做这件事。
07:12
So what have we learned to date?
132
432100
2177
到现在我们从这些数据中学到了什么呢?
07:15
Gender.
133
435057
2331
性别差异。
07:17
Our data confirms something that you might suspect.
134
437388
3646
我们的数据证实了某些你可能正在猜测的事情。
07:21
Women are more expressive than men.
135
441034
1857
女性比男性更具表现力。
07:22
Not only do they smile more, their smiles last longer,
136
442891
2683
不仅是她们笑得更多,更因为她们笑得更久,
07:25
and we can now really quantify what it is that men and women
137
445574
2904
并且我们现在可以真实地量化男性和女性
07:28
respond to differently.
138
448478
2136
在反应方面的差异性。
07:30
Let's do culture: So in the United States,
139
450614
2290
让我们从文化方面来看:在美国,
07:32
women are 40 percent more expressive than men,
140
452904
3204
女性的表现力要比男性高40%,
07:36
but curiously, we don't see any difference in the U.K. between men and women.
141
456108
3645
但奇怪的是,在英国我们看不到男女在这方面的任何差异。
07:39
(Laughter)
142
459753
2506
(笑声)
07:43
Age: People who are 50 years and older
143
463296
4027
在年龄方面:50岁及以上的人
07:47
are 25 percent more emotive than younger people.
144
467323
3436
情绪化比小于50岁的人高25%。
07:51
Women in their 20s smile a lot more than men the same age,
145
471899
3852
女性在20来岁的时候要比同龄的男性笑得更多,
07:55
perhaps a necessity for dating.
146
475751
3839
也许这是约会的必需品。
07:59
But perhaps what surprised us the most about this data
147
479590
2617
但也许这些数据带给我们最大的惊喜是
08:02
is that we happen to be expressive all the time,
148
482207
3203
我们每时每刻都在表达,
08:05
even when we are sitting in front of our devices alone,
149
485410
2833
即使当我们独自坐在电子设备前,
08:08
and it's not just when we're watching cat videos on Facebook.
150
488243
3274
而且不仅是我们在脸书上看猫的视频时。
08:12
We are expressive when we're emailing, texting, shopping online,
151
492217
3010
不管我们在发邮件、发短信、网购,甚至报税的时候
08:15
or even doing our taxes.
152
495227
2300
我们无时无刻不在表达自己。
08:17
Where is this data used today?
153
497527
2392
那么如今这些数据用在何处呢?
08:19
In understanding how we engage with media,
154
499919
2763
用在弄明白我们如何和传媒结合,
08:22
so understanding virality and voting behavior;
155
502682
2484
从而搞明白网络扩散和投票行为,
08:25
and also empowering or emotion-enabling technology,
156
505166
2740
以及情绪授权技术。
08:27
and I want to share some examples that are especially close to my heart.
157
507906
4621
我想分享一些触动我心的例子。
08:33
Emotion-enabled wearable glasses can help individuals
158
513197
3068
情绪授权可佩戴眼镜
08:36
who are visually impaired read the faces of others,
159
516265
3228
可以帮助那些视力受损的人读懂他人的脸部表情,
08:39
and it can help individuals on the autism spectrum interpret emotion,
160
519493
4187
也可帮助患有自闭症的人们解读情绪,
08:43
something that they really struggle with.
161
523680
2778
因为解读情绪对他们来说是很困难的。
08:47
In education, imagine if your learning apps
162
527918
2859
在教育方面,想象如果你的学习类应用程序
08:50
sense that you're confused and slow down,
163
530777
2810
察觉出你有困惑,应用程序会放慢速度,
08:53
or that you're bored, so it's sped up,
164
533587
1857
或者你无聊了,它则会加快进程,
08:55
just like a great teacher would in a classroom.
165
535444
2969
就像教室里经验丰富的老师一样。
08:59
What if your wristwatch tracked your mood,
166
539043
2601
再想象一下你的手表可以感知你的情绪,
09:01
or your car sensed that you're tired,
167
541644
2693
或你的车可以觉察出你疲惫了,
09:04
or perhaps your fridge knows that you're stressed,
168
544337
2548
或者说你的冰箱知道你有压力,
09:06
so it auto-locks to prevent you from binge eating. (Laughter)
169
546885
6066
所以它会自动上锁防止你暴饮暴食。(笑声)
09:12
I would like that, yeah.
170
552951
2717
我会喜欢这个的,没错。
09:15
What if, when I was in Cambridge,
171
555668
1927
设想当我在剑桥时,
09:17
I had access to my real-time emotion stream,
172
557595
2313
我可以连接到实时情绪流,
09:19
and I could share that with my family back home in a very natural way,
173
559908
3529
我可以和我家里的亲人 用很自然的方式分享一些东西,
09:23
just like I would've if we were all in the same room together?
174
563437
3971
就像我和家人在同一间房里所做的事一样将会怎样?
09:27
I think five years down the line,
175
567408
3142
我猜想也就在五年后,
09:30
all our devices are going to have an emotion chip,
176
570550
2337
所有的电子设备都会有一个情绪芯片,
09:32
and we won't remember what it was like when we couldn't just frown at our device
177
572887
4064
我们将会体验到我们皱眉后电子设备回应 “嗯,你不喜欢这个,对吧?”
09:36
and our device would say, "Hmm, you didn't like that, did you?"
178
576951
4249
这一举动实现时的感受。
09:41
Our biggest challenge is that there are so many applications of this technology,
179
581200
3761
我们最大的挑战就是 现在关于这方面的科技有许多用途,
09:44
my team and I realize that we can't build them all ourselves,
180
584961
2903
我和我的团队意识到我们无法 靠我们自己就把所有事情都完成,
09:47
so we've made this technology available so that other developers
181
587864
3496
所以我们把这项科技开放,
09:51
can get building and get creative.
182
591360
2114
这样其他开发者就能创造创新。
09:53
We recognize that there are potential risks
183
593474
4086
我们知道这有潜在的风险,
09:57
and potential for abuse,
184
597560
2067
还有可能被滥用,
09:59
but personally, having spent many years doing this,
185
599627
2949
但就我个人来说,花了这么多年做这件事,
10:02
I believe that the benefits to humanity
186
602576
2972
我相信情绪智能技术
10:05
from having emotionally intelligent technology
187
605548
2275
给人类带来的好处
10:07
far outweigh the potential for misuse.
188
607823
3576
远超过被滥用的可能性。
10:11
And I invite you all to be part of the conversation.
189
611399
2531
所以我邀请大家一起加入。
10:13
The more people who know about this technology,
190
613930
2554
越多的人知道这项技术,
10:16
the more we can all have a voice in how it's being used.
191
616484
3177
我们就越能说出如何使用的想法。
10:21
So as more and more of our lives become digital,
192
621081
4574
所以随着我们的生活越来越数字化,
10:25
we are fighting a losing battle trying to curb our usage of devices
193
625655
3498
我们其实在打一场处于劣势的战争,试图去控制我们的电子设备的用途
10:29
in order to reclaim our emotions.
194
629153
2229
从而开拓我们的情绪。
10:32
So what I'm trying to do instead is to bring emotions into our technology
195
632622
3914
所以相反地,我所做的就是把情绪带到我们的科技中
10:36
and make our technologies more responsive.
196
636536
2229
让我们的科技更加有响应性。
10:38
So I want those devices that have separated us
197
638765
2670
我想要那些把我们分离开来的电子设备
10:41
to bring us back together.
198
641435
2462
重新把我们聚在一起。
10:43
And by humanizing technology, we have this golden opportunity
199
643897
4588
现在是黄金时机,我们可以通过人性化科技
10:48
to reimagine how we connect with machines,
200
648485
3297
重新想象我们该如何和这些机器交流结合,
10:51
and therefore, how we, as human beings,
201
651782
4481
从而重新想象,作为人类的我们
10:56
connect with one another.
202
656263
1904
如何与彼此交流结合。
10:58
Thank you.
203
658167
2160
谢谢。
11:00
(Applause)
204
660327
3313
(掌声)
关于本网站

这个网站将向你介绍对学习英语有用的YouTube视频。你将看到来自世界各地的一流教师教授的英语课程。双击每个视频页面上显示的英文字幕,即可从那里播放视频。字幕会随着视频的播放而同步滚动。如果你有任何意见或要求,请使用此联系表与我们联系。

https://forms.gle/WvT1wiN1qDtmnspy7