Have the creators of this project considered the privacy implications of capturing, recording, or analyzing audio from the rainforest? What happens if people are walking near a microphone and a conversation is picked up by the microphones? I realize that the audio is probably analyzed for the sound of chainsaws, and then thrown away, but there's still the potential that such a system could be misused. So just wonderi…
Listening for illegal logging chainsaws using TensorFlow
41–50 of 128 posts
Re: Listening for illegal logging chainsaws using TensorFlow
#42Have the creators of this project considered the privacy implications of capturing, recording, or analyzing audio from the rainforest? What happens if people are walking near a microphone and a conversation is picked up by the microphones? I realize that the audio is probably analyzed for the sound of chainsaws, and then thrown away, but there's still the potential that such a system could be misused. So just wonderi…
Re: Listening for illegal logging chainsaws using TensorFlow
#43I'm not too familiar with ML, do you have to "train" tensorflow as to what audio in the data is "definitely a chainsaw" and which is "definitely a logging truck", etc etc? As in, you should keep doing this every now and then as you get more and more data, at least in the sense of flagging false positives (so as to unlearn that particular sound).
Yes. In the video there is a short snippet where the audio is shown as a Fourier transformed image on the screen and a user is annotating the image of the sound using red boxes. This is a part of the process to train the ML model to recognize chainsaw sounds vs. other sounds.
Re: Listening for illegal logging chainsaws using TensorFlow
#44Earlier quoted context omitted.
This is a myth, mostly. First of all: no jail. This is civil law, not criminal. Second: it's pretty hard not to have an excuse to do anything you want if you're the board + management. Google, and most other companies, give to charitable organisations, for example. "Now", you'll say, "they're just doing this for PR". Maybe... But using the PR argument actually works perfectly fine for anything altruistic a company ma…
Defrauding investors yields jailtime more often than not. Depending on the particular case is might be a civil case, but even civil cases often result in incarceration. I'm not going to argue with the rest of your post because your belief that a company might be doing " anything altruistic " is just sad for me, perhaps laughable for others.
Re: Listening for illegal logging chainsaws using TensorFlow
#45Hey Topher! Are you guys cross checking this with daily satellite imagery? I met with a guy who's company gets a full HD shot of the earth every 24 hours and they'd be happy to give you guys access to the visual data (they also train algorithms on it to detect all sorts of activity).
Anyhow, I'll shoot you an email.
Re: Listening for illegal logging chainsaws using TensorFlow
#46Earlier quoted context omitted.
This is a really cool application of this technology, great work! Do you have any blog posts explaining the types of models you're using or open source repos that one could contribute to? (Asking as a ML/Software Engineer who's pleasantly surprised and yearning to contribute to something like this!)
Thanks! We are a relatively small engineering team and we were mainly focused on improving our system. This took a lot of effort and time, we just haven't had a chance yet to think about open sourcing or blogging. Our days were focused on coding. If there's interest in blog posts, I could write up some of our technology. Just let me know whether there's an interest and what you'd like to know.
Re: Listening for illegal logging chainsaws using TensorFlow
#47Earlier quoted context omitted.
Yeah it's pretty naive. Google trying to make the world a better place would actually be illegal and would place the managers in jail for defrauding investors. Google's mission is to make as much money as possible, typical tactics include creating a good corporate image.
No google mission is to maximize shareholder value. Making the world a better place increases shareholder value and is therefore compatible with their mission ;-)
I think most people dramatically underestimate the amount of resources Google invests in all sorts of programs (including R&D, charitable donations, education, partnerships and so much more) because 1) they don't use it as a negotiating tactic, and 2) the cash cow of the ads business provides an enormously long leash for experimentation and.
Even with Apple, which has more than double the cash (and cash flow), doesn't have this flexibility because of its business model. As a hardware company, volumes, revenue & margin are predictable and anticipated, baked into the stock price with an assumption of -- for the last few years -- dividends. Amazon is at the other extreme. Until very recently, as a result of AWS' runaway success, Amazon had posted negative-to-zero profits for its entire history, reinvesting nearly 100% of free cash flow into business expansion.
No matter what you might think of Google, among the huge tech companies they're unique in their ability to spend enormous sums on things that absolutely do not directly increase shareholder value. The belief within the company, and within the investment community, that some of these moonshots & experiments will eventually stimulate stepwise returns are why they continue to run this way. It's cultural, and ultimately, one of the foundations of "googleyness".
Re: Listening for illegal logging chainsaws using TensorFlow
#48Anyone else wonder if google's on a massive PR drive given all the privacy-related bad press that tech has been getting recently?
https://www.blog.google/topics/google-cloud/extending-gcp-se...
Re: Listening for illegal logging chainsaws using TensorFlow
#49Have the creators of this project considered the privacy implications of capturing, recording, or analyzing audio from the rainforest? What happens if people are walking near a microphone and a conversation is picked up by the microphones? I realize that the audio is probably analyzed for the sound of chainsaws, and then thrown away, but there's still the potential that such a system could be misused. So just wonderi…
Re: Listening for illegal logging chainsaws using TensorFlow
#50Earlier quoted context omitted.
This is a really cool application of this technology, great work! Do you have any blog posts explaining the types of models you're using or open source repos that one could contribute to? (Asking as a ML/Software Engineer who's pleasantly surprised and yearning to contribute to something like this!)
Thanks! We are a relatively small engineering team and we were mainly focused on improving our system. This took a lot of effort and time, we just haven't had a chance yet to think about open sourcing or blogging. Our days were focused on coding. If there's interest in blog posts, I could write up some of our technology. Just let me know whether there's an interest and what you'd like to know.