ADM-201 dump PMP dumps pdf SSCP exam materials CBAP exam sample questions

【人工智能实验系列】机器学习分辨鸟鸣 – 译学馆
未登陆,请登陆后再发表信息
最新评论 (0)
播放视频

【人工智能实验系列】机器学习分辨鸟鸣

A.I. Experiments: Bird Sounds

[音乐]
[Music Play]
大家好 我是Kyle
Hi, I’m Kyle.
我是Manny
I’m Manny.
嗨!我是Jessie 来自康奈尔鸟类研究所
Hey, I’m Jessie, from the Cornell Lab of ornithology.
这是一次我们使用机器学习进行的实验
This is an experiment we made that uses the machine learning
我们将收集的上千种鸟类声音形成跟踪可视图
to organize thousands of bird sounds into the tracked visualization.
因为鸟的种类很多 鸟鸣很难区分
Bird sounds can be really difficult to learn because there are so many species out there.
有些鸟类的叫声真的很相似
And some of them sound really similar,
有时你 可能需要在升调的鸟鸣和
and at times you might just need to be distinguishing between the notes that slurs up
降调的鸟鸣中区分出它们 这其实是非常非常细小的差别
or notes that you know drops a pitch, and this can be really really subtle differences.
项目开始于我们与康奈尔的人在聊
This project started when we were talking to people at Cornell
如果用机器学习来处理鸟鸣可能会是怎样的一件趣事
about how it might be interesting to play machine learning to bird sounds.
于是我们打算用采集来的鸟叫声做个小测试
So we decided to try a little test with some of the sounds in a collection.
我们没有提前给电脑输入任何外部数据意见或编辑标签 甚至是输入鸟类名称
We didn’t give the computer any outside data or tags, or even tell in the birds names.
我们希望看到 电脑是否能够仅靠听取鸟叫声自动检索识别出它们
We wanted to see if it could just listen to the sounds then automatically learn in its own way to organize them.
鸟鸣有多种多样的变化 所以当我们在同一空间观察它们之前
Bird sounds vary a lot. So before we can look at them in the same space,
我们不得不将所有的声音都分解成不超过一秒的声音片段
we have to break down everything in short burst of sound less than a second long.
我们把这种声音分组的手法称为t-SNE
Then we group the sounds for the technique called t-SNE.
首先 电脑创建了一种类似于采集“指纹”的形式 每段声音都如同一种影像
First computer creates a fingerprint form each sound which is like an image
或者一系列代表特殊样本的数字
or a set of numbers that represents that particular sample.
之后t-SNE会对所有“指纹”的进行比较 以及相近位置处相似的声音对比
Then t-SNE compares all these fingerprints ,and places similar sounds close together.
理解t-SNE的一种方式
One way to think about t-SNE
是它可以从高维空间捕捉“指纹”
is that it is taking the fingerprints from a high-dimensional space.
这是个超过三维的空间
That’s spaces were more than three dimensions
然后降低到二维空间后 就能够可视化
and reducing them to two dimensions, so we can visualize them.
我们的测试很成功 这是一张用电脑创建的声音示意图
And our test worked pretty well. This is a map of sounds that computer created.
你能看到这项系统是如何解决从临近的相近的鸟鸣声中对其进行分组的过程
You can see that it figured out how to group similar sounds from similar birds close together.
以便我们能从中搜寻到特定的鸟类
We also made it so that you can search for specific birds.
我们将其传到互联网上与大家共同分享
We put it on the web for you to play with.
当然 我们还有一个远大的梦想 那就是 未来的某天你能够
We certainly have a dream that some day you will be able to put out
在亚马逊雨林里安装一个带有录音功能的麦克风
a microphone in the Amazon with a recorder and have all the species
不仅能对鸟鸣进行辨认 一些你不知道的生物也能辨认出来
you know even not even just birds identified and
通过自动识别这项科学技术
we will be able to monitor species diversities outside
我们就能监控外界物种的多样性
through the automated recognition techniques.
利用电脑科学技术
I think it’s incredibly exciting to figure out
与鸟类学 综合生物学之间进行协作
what those collaborations that we can make between computer science
处理一些令人激动 又具有挑战性的科学保护问题
and ornithology or biology general and start to tackle some really exciting
我想这会让我们获得难以置信的兴奋感
and challenging science conservation questions.
欢迎访问MacaulayLibrary.org获得更多声音资源
Visit MacaulayLibrary.org for more resources on a lot of life sounds.
你也可以从 g.co/aiexperiments网站获取源码 参与这项试验 来试试吧~
And you can play with this experiment we made and get code at g.co/aiexperiments.

发表评论

译制信息
视频概述

研究人工智能,通过机器学习的方法对鸟类的声音进行收集辨识。

听录译者

[B]无牙无耳

翻译译者

[B]无牙无耳

审核员

知易行难

视频来源

https://www.youtube.com/watch?v=31PWjb7Do1s

相关推荐