Ha ha, funny idea! After examining my own behaviour the other day I realised that if I ever owned a store that faced the street, I would totally put a microphone in the window to get customer feedback from after-hours window-shoppers: you can't solicit that kind of honesty!
At the grocery store the other day, my wife and I were deciding between a few items. The thought occurred to me that a microphone in the aisle would be huge for customer feedback! A few seconds later I realized that it would just be a feed of people yelling at their kids/spouses... not very helpful.
We work with a decent number of older, non technical people, and our product team would love to be a fly on the wall to hear where they're frustrated in the product. Obviously due to security concerns we could never implement something like this, but in a perfect world this would be a killer feature.
You only need to per-visit when it's an insecure localhost endpoint or something similar IIRC. (or if you have an extension which clears that setting every page load)
My original idea was going to involve a dependency on one of the bad words lists available on npm, but then I saw the API censors said words and thought, "Oh, that's easy."
It's also interesting to see which words Google determines is bad, and which they mysteriously don't. The API does real time processing of sentence structure and will return "<three asterisks> on me" and "cum to the park" correctly, based on intent. (Sorry for the offensive speech!)
For a side project I needed to find every single English word/phrase the API would filter. Stumbled upon that in amazement.
(Side note: speaking a long list of bad words into a microphone very slowly was the most fun QA I've done)
> My original idea was going to involve a dependency on one of the bad words lists available on npm, but then I saw the API censors said words and thought, "Oh, that's easy."
I always found this hilarious, my phone won't let me swear in a text I am sending using voice to text but it will gladly boom "fuck" over my car's Bluetooth when someone sends me a text with swear words.
Since the voice recognition isn't perfect it means there is a chance it could make false positives and write a bad word you didn't say. Then people complain to Google or sue them. Similarly google search won't auto suggest offensive words or certain libelous statements (e.g. "X is a criminal", even if they are, and even if its a common search phrase.)
I think he's trying to show that the speech API is smart enough to understand the context of the phrase and is not just blindly replacing words based on spelling.
I get that this is a free service and all, but I find that ridiculous. They are basically crippling the functionality of a service that is global and it is not aimed at a particular application, based on a very localized interpretation of what is nice to say and what is not... this should be controlled at the application level, the API providing at most hints about the tone.
Depending on what you use it on, this could render the service useless. Imagine using it to, I don't know, trying to identify Pulp Fiction sentences against a corpus of scripts. It would fail spectacularly.
Another example context on where this could fail very quickly is when considering people from other languages, e.g., if I'm not wrong, saying "Jesus!" might be impolite in (some contexts of) the US. In Spain, we say "Jesus!" when you sneeze, instead of "Bless you!" (and, in general, we are outrageously foul-mouthed compared to the US).
Ignoring the unlikelihood of someone actually authorizing microphone permissions (because it's no fun if we take that into consideration), what are some good use cases for this library.
Reminds me of those rumors that swearing at an automated phone system will usually cause it to direct you to a human operator. I've never given it a try myself to see if it's true.
Nifty idea - but I couldn't trigger it. Must be because it detected my sweet choir boy nature, and knew that my attempts at profanity was 'cute' rather than grumpy!
(Just kidding, for those who can't detect sarcasm. That's a killer idea - build an app that detects sarcasm in text, deploy on HN, have a happier community.)
Wow, because I really want to have my computer listening in on everything I say and snitching (with context) to an unknown listener if I say a bad word.
46 comments
[ 3.1 ms ] story [ 99.2 ms ] threadWe work with a decent number of older, non technical people, and our product team would love to be a fly on the wall to hear where they're frustrated in the product. Obviously due to security concerns we could never implement something like this, but in a perfect world this would be a killer feature.
You only need to per-visit when it's an insecure localhost endpoint or something similar IIRC. (or if you have an extension which clears that setting every page load)
See for example George Carlin's "Seven dirty words" as returned by the SpeechRecognition demo https://cl.ly/3A1F0r3U1H1D/Screen%20Shot%202016-09-03%20at%2...
(The anti-feature being the enforcement of American prudity onto what should be an indifferent API.)
https://github.com/knpwrs/grumbles.js/blob/master/src/grumbl...
It's also interesting to see which words Google determines is bad, and which they mysteriously don't. The API does real time processing of sentence structure and will return "<three asterisks> on me" and "cum to the park" correctly, based on intent. (Sorry for the offensive speech!)
For a side project I needed to find every single English word/phrase the API would filter. Stumbled upon that in amazement.
(Side note: speaking a long list of bad words into a microphone very slowly was the most fun QA I've done)
> My original idea was going to involve a dependency on one of the bad words lists available on npm, but then I saw the API censors said words and thought, "Oh, that's easy."
Depending on what you use it on, this could render the service useless. Imagine using it to, I don't know, trying to identify Pulp Fiction sentences against a corpus of scripts. It would fail spectacularly.
Another example context on where this could fail very quickly is when considering people from other languages, e.g., if I'm not wrong, saying "Jesus!" might be impolite in (some contexts of) the US. In Spain, we say "Jesus!" when you sneeze, instead of "Bless you!" (and, in general, we are outrageously foul-mouthed compared to the US).
> In Spain, we say "Jesus!" when you sneeze, instead of "Bless you!" (and, in general, we are outrageously foul-mouthed compared to the US).
..it may sound as if "¡Jesús!" ("Bless you!") is foulmouthed - when in fact is something a four-year-old would typically say.
Reminds me of those rumors that swearing at an automated phone system will usually cause it to direct you to a human operator. I've never given it a try myself to see if it's true.
Any links are appreciated
(Just kidding, for those who can't detect sarcasm. That's a killer idea - build an app that detects sarcasm in text, deploy on HN, have a happier community.)
https://tone-analyzer-demo.mybluemix.net/
Is there a southern grandma setting?
HURRAY! And, it never shall.
Cool tech. Uncool use.