演讲文本

In order to convert this opaque, 90,000 hours of video into something that we could start to see,
为了把这个9万小时的录像变成我们能识辨的东西
we use motion analysis to pull out, as we move through space and through time, what we call space-time worms.
我们用行动分析来抽取我们在时空的移动，我们称之为时空虫。
And this has become part of our toolkit for being able to look and see where the activities are in the data,
这个成为了我们工具的一部分，用来观察和辨识数据中的各种活动
and with it, trace the pattern of, in particular, where my son moved throughout the home,
再利用这个办法去追踪模型，特别是我儿子在家去过哪些地方
so that we could focus our transcription efforts, all of the speech environment around my son
使得我们能够聚焦解读我儿子学习语言的语境
all of the words that he heard from myself, my wife, our nanny, and over time, the words he began to produce.
他从我，我妻子和保姆那里听到的所有词汇，渐渐的，他开始使用的词汇

So with that technology and that data and the ability to, with machine assistance, transcribe speech,
因此通过技术和数据，在机器的协助下录制下对话
we've now transcribed well over seven million words of our home transcripts.
我们现在已经完成了超过7万字的家庭言谈的记录
And with that, let me take you now for a first tour into the data.
现在，让我带你们进入这些数据的第一个旅行
So you've all, I'm sure, seen time-lapse videos where a flower will blossom as you accelerate time.
我相信，你们大家都看过时间推移的影片，加快时间的推移你可以看见花朵盛开
I'd like you to now experience the blossoming of a speech form.
现在我让你们看看语言的花朵是怎样绽放的
My son, soon after his first birthday, would say "gaga" to mean water.
我的儿子，在他的第一个生日后，会说“gaga”来指水
And over the course of the next half-year, he slowly learned to approximate the proper adult form, "water."
在这之后的半年里，他渐渐地学会了成年人说的正确的“水”
So we're going to cruise through half a year in about 40 seconds.
我们现在来用40秒时间快速浏览这半年
No video here, so you can focus on the sound, the acoustics, of a new kind of trajectory: gaga to water.
没有影像，所以你们可以专注听声音，声学上的，这种新的轨迹变化，从“Gaga"到"Water"。

视频及简介

演讲简介：

麻省理工大学的研究员戴·罗伊希望了解他的初生儿子是怎样学习语言的，因此他在家里四处装置了摄像机捕捉儿子成长的几乎每一刻，然后将9万小时的家庭录像进行分析，观察“gaaaa”渐渐转变成“水”的过程。这一惊人的资料丰富的研究对帮助我们了解人类是如果学习起到了深远的作用。