科学美国人60秒:计算程序可预测夫妻问题
日期:2016-08-12 11:56

(单词翻译:单击)

m,SD(BHc-Ng19@M!oVUb3OEkz6VOP

听力文本

OrDe7!|WOJ|a

This is Scientific American — 60-Second Science. I'm Erika Beras.
Got a minute?
Watch your tone—because it turns out it really isn't what you say—it's how you say it. At least when it comes to couples in couples counseling.
That's according to a study in Proceedings of Interspeech.
Researchers developed a computer algorithm to gauge relationships between spouses based on their vocal patterns. Working with hundreds of recorded conversations from marriage therapy sessions collected over two years, the algorithm was able to predict whether a relationship was going to get better or worse with an accuracy of just under eighty percent.
How they did it? The recordings were divided by acoustic features that used speech processing techniques to track pitch and voice warble and intensity.

C|9I#;qeIaLzjqhJP

夫妻关系.jpg

P1.XUfHsXTo87

These clips from the researcher's training video illustrate psychological states that characterize distressed relationships. This one, for example, shows “negative affect” and “reactivity” – behaviors that relationship experts believe are troublesome.
Female: And I want you to just come home at a more reasonable time rather than you know walking in the door at 11.
Male: I just don't think you understand just how much I have to do, what my work entails.
Female: Well, what is there to understand?
The counseling sessions were also tested against behavioral analyses with codes for positives such as “acceptance” and the negatives such as “blame.” Using only that more standardized research method wasn't as predictable as listening to the vocal expressions.
Now, these examples are negative as the researchers focused on distressed relationship dynamics. One could imagine the algorithms may also work the same way when looking at positive vocal patterns. Because even married couples sometimes say nice things to each other.
Thanks for the minute for Scientific American — 60-Second Science Science. I'm Erika Beras.

p3SLt3@l_aCV*yJFyE

m,ape4u39k@UGN!of~&f

参考译文

S;UsiI*DxgB7HhXi|w)

这里是科学美国人——60秒科学ASaYv.0Lb[7O^Z|+7wP。我是艾丽卡·贝拉斯MPNo0l&f_+Q=!6y
有一分钟时间吗?
注意你的语调,事实证明你说什么并不重要,重要的是你怎么说IZ8mge%8L.,tWb。至少在夫妻关系咨询方面是这样4@eCJ_dtFFM
这一研究结果发表在《Interspeech学报》上fF^*8rBHGW^HNoq_
研究人员研发出一种计算机算法,依据声音模式来衡量夫妻之间的关系m%L0YB9KdGceXCQO。通过对两年多以来搜集到的数百条婚姻治疗对话记录进行分析,该算法可以预测一段关系是会变好还是会变差,预测准确率接近80%#66j.9P2;|m@JJHNe5
这是如何做到的?使用语音处理技术追踪语调的起伏、颤动和强度,然后根据声学特征对录音进行区分(DY_x]X&*1!!dPxPNFMy
这些研究人员的培训视频片段能够表明不良关系的心理状态Oyo~![w=~f.DH~SPTmg。例如,两性关系专家认为“消极情感”及“反应”等行为会造成麻烦=1~JY*7Xy;
女性:我只是希望你能在一个更合理的时间回家,而不是11点才走进家门ED=(&t20+]mz
男性:我认为你并不理解我有多少事要做,也不理解我的工作需要dWDf|Q,qnJjqs1#~At2
女性:好吧!我有什么需要理解的?
咨询课程还对“接受”等积极代码和“责备”等消极代码进行了行为分析测试0hiK;k7MRmV2lo。只使用更加标准化的研究方法并不像聆听声音所表达出来的内容那样有可预见性)Uq-~r!thyec%L3
目前,由于研究人员关注的是不良关系的动态,因此这些例子都是负面的L#HRtI2hy+@。人们可能会设想,这种算法也可以采用同样的方式处理积极声音模式0-tx*JC&gSe%。因为即便是已婚夫妻有时也会互相说说好话YoM(7yLzQ]AMn_
谢谢大家收听科学美国人——60秒科学mu9u4M_zW3]HBaz^y(,I。我是艾丽卡·贝拉斯G0^~F=+EVUuxzcSR=0

.I&Zz7H6f7!ESw

Ax#3;xj+b#!@8

译文为可可英语翻译,未经授权请勿转载!

Hak57EUsRH+ZU

0c_37tLc,Qd)e&+C3GUs

重点讲解

%B*9k;cGA]u

!#jv=JE5YtB|

重点讲解:
1. turn out 原来是;结果发现;
例句:It turned out that my surmise was correct.
结果表明我的推测没有错Dv7&i[wdm9CEC
2. when it comes to 谈论;谈到;
例句:When it comes to cooking I know nothing.
说到做饭,我是一窍不通([Z5,DiLk+GqFLX;p
3. be based on 以…为基础;
例句:Capitalism is based on private ownership.
资本主义是建立在私有制基础上的HRaSar3arMT=J#
4. rather than 而非;胜于;而不是;
例句:I like walking on grass rather than paths, it's so much softer.
我宁愿在草地上面走而不愿走小路,草地柔软多了o.V-D*;TTS5xR_]|
5. focus on 集中(注意力);关注;
例句:The other two groups focus on future improvements.
另外两类人关注未来的改进TT^]SfDGvgfCSd

1-*DHY&M|gnDm(Of

dHTyuriejsx~T1Lb|G+TxlY|3%w!=5#)U=eCh7]G=X*
分享到