Microsoft Gets Patent for Patently Offensive Audio Content

October 28, 2008 by Mary Anne Simpson weblog
Microsoft Gets Patent for Patently Offensive Audio Content
US Patent and Trademark Expo

( -- Microsoft recently obtained a patent designed to create an Automatic Censorship of Audio Data For Broadcast . The invention is intended to act as a filter for live broadcasts where it is impracticable to delete or make inaudible certain undesired words or phrases. Additionally, other audio streams like music or games can utilize the automatic censor.

An input audio data stream comprising speech is processed by an automatic censoring filter in either real time mode or batch mode, producing censored speech that has been altered so the undesired words or phrases are either unintelligible or inaudible. The substituted speech is not bleeped out, but modified in the speakers own voice.

According to the patent abstract, the reason for the invention is that it is common for radio and and television broadcasts of live events to be delayed a few seconds before the audio data is transmitted to enable real-time (censors) content reviewers to evaluate whether the content contains objectionable language. Broadcast television and radio are heeding the demand by the public to essentially "clean up" the airways for the general public and children in particular. The degree of censorship depends on the targeted audience and the nature of the event. Specifically, certain words which are commonly referred to as profanity, obscenities and sexually explicit words are targeted by censors to be unacceptable for public broadcasting.

In certain situations where there are multiple individuals speaking as in a game-play scenario it is almost impossible for a human censor to catch all extraneous remarks or words. This is where the Automatic Censorship of Audio Data for Broadcast fills in the gaps. Instead of bleeping out objectionable language, the patent will essentially supply a substitute phrase or word or make the word inaudible to the listener. While the patent can employ the "bleeping" of objectionable words, it will attempt to overwrite the objectionable content with a more acceptable term or word. The acceptable word or phrase is created by using previously uttered phonemes of the speaker that can be combined to produce the more acceptable version. Thus, the censored content appears and sounds like the speaker´s own words.

The Automatic Censorship of Audio Data for Broadcast patent is not without its critics. On-line forums and bloggers are not uniformly impressed with the patent. According to one comment on Slashdot, "Come on, if you´re old enough to play the game, you´re old enough to either deal with it or tell them to stuff a sock in it." Other comments include the impossible task of coding various types of a new breed of curse words. To wit, another commentator congratulates Microsoft for expanding the lexicon of profanity to include a more creative style of profanity and obscenity in order to fool the program.

One thing is for sure, the Automatic Censorship of Audio Data for Broadcast evokes a discussion on the subject of censorship. Comments are welcome on this post without %$&# included, if at all possible.

Explore further: Google envisions delivery of AR elements to physical books

Related Stories

Google envisions delivery of AR elements to physical books

March 6, 2016

The mind at its laziest sees the old—books in print—and the new—the digital universe—as opposites, in an either-or historic transition from one to the other. Goodbye, brick and mortar book shops, hello, Kindle. Reading ...

Playback: 130-year-old sounds revealed

December 15, 2011

( -- In the early 1880s, three inventors—Alexander Graham Bell, Chichester Bell and Charles Sumner Tainter, collectively making up the Volta Laboratory Associates—brought together their creativity and ...

Recommended for you

New method analyzes corn kernel characteristics

November 17, 2017

An ear of corn averages about 800 kernels. A traditional field method to estimate the number of kernels on the ear is to manually count the number of rows and multiply by the number of kernels in one length of the ear. With ...

Optically tunable microwave antennas for 5G applications

November 16, 2017

Multiband tunable antennas are a critical part of many communication and radar systems. New research by engineers at the University of Bristol has shown significant advances in antennas by using optically induced plasmas ...


Adjust slider to filter visible comments by rank

Display comments: newest first

5 / 5 (11) Oct 28, 2008
Wow, that's creepy! Especially the part of replacing the offensive language in a way that makes it sound like it wasn't censored. Like in 1984 where Big Brother controls speech by removing words from the dictionary.
They probably got the idea from that Mac commercial where PC presses the buzzer when Mac tries to say 'Vista'. Or should I say V*&^$?
4.9 / 5 (9) Oct 28, 2008
Thus, the censored content appears and sounds like the speaker's own words.

Now that's scary. Talk about putting words into somebody else's mouth.
What happens when someone finds the inserted words objectionable?
A modified version of this could make for interesting debates!
...or Used Car ads "Come down and see the, uh, mile of cars we have on our lot."
4.8 / 5 (5) Oct 28, 2008
Wow, very 1984-ish. If technology like this is ever created I'm already patently against it. Censorship on that level is just absurd.
4.8 / 5 (4) Oct 28, 2008
They probably got the idea from that Mac commercial where PC presses the buzzer when Mac tries to say 'Vista'. Or should I say V*&^$?

That's a good one. XD
4.8 / 5 (5) Oct 28, 2008
i cant wait till china gets a hold of this. all their broadcasts will be digitized and then filtered in a 5 second delay or something. eventually this may even work on realtime. scary.
1 / 5 (12) Oct 28, 2008
Go Microsoft!!!
It is always more efficient to squelch the source of noise rather than cleaning the many messes it makes everywhere it goes. What Microsoft is doing is the antithesis of this and they are pretty ambitious to try it. Let's _all_ hope it works! Anyone who doesn't want it to work is a sociopath who needs help.
4.9 / 5 (7) Oct 28, 2008
Wow, very 1984-ish. If technology like this is ever created I'm already patently against it. Censorship on that level is just absurd.

Sadly, it's doable now on a basic level. Making it foolproof and seamless will be much harder. On video you would get a "Godzilla effect", the words won't match the mouth movements. I can imagine people would have fun with saying completely obscene things without using curse words.
As an aside I'd like to recommend the novel "Little Brother" by Mitch Kapor. A very smart and engrossing story that deals with issues of technology and freedom.
3.3 / 5 (3) Oct 28, 2008
What next? They will make the lip movement and expressions match the phrases they want to include. That way no one ever has to say anything at all. We can just rely on good old Uncle Sam to feed us anything he wants.
4.5 / 5 (2) Oct 28, 2008
As an aside I'd like to recommend the novel "Little Brother" by Mitch Kapor.

Ack! That's Cory Doctorow, not Mitch Kapor! Mitch's name was on the dust cover because he was recommending it. I should have gotten up to check. My bad.
5 / 5 (3) Oct 28, 2008
This is outrageous! This level of censorship is unacceptable. Just where would this end? Will microsoft filter what I can say through my MSN? E-mails? TeamSpeak during games? This is criminal intrusion into personal life.

I can already see it now. I'm watching a porn movie online and the girl goes "Oh Yes! Sexually please me!"

Unless a program like this can be turned off by the user at will I doubt if it's even in accordance with freedom of information.
5 / 5 (2) Oct 28, 2008
Can somebody include the word Microsoft in the Automatic Censorship of Audio Data for Broadcast databases...:-)
not rated yet Oct 28, 2008
Unfortunately there will be those who will applaud this as progress. Whats next a downloadable version that you can load on your cell phone that will edit out objectionable material. I find this disheartening. I wonder how long it will be till so called seditious speech is edited out. I hope that one day Every TV, Radio, and phone will have this device, wait did I actually say that?
4 / 5 (1) Oct 28, 2008
This still doesn't block people that want to be obscene on air, in fact it makes it easier. A manual censor might be able to notice that "Mother Fpucker" is inappropriate for children, but an automated system that could catch that would probably have too many false positives to be useful.

Both the automated and manual systems are also vulnerable to the "slow obscenity" hole. If a live broadcast is on a 5 second delay, you just have to say your obscenity very slowly so that it takes 6 seconds to say, and now it won't be caught. Of course this isn't practical for common use, but I'm sure comedians could have fun with it.
3 / 5 (2) Oct 28, 2008
...or Used Car ads "Come down and see the, uh, mile of cars we have on our lot."

I remember that movie :)
not rated yet Oct 28, 2008
The entertainment value of the content will _skyrocket_ if Microsoft also edits the lip movement to match the aliased speech (a'la Monte Python)! In fact, they MUST do it or it will continue to offend the hearing impaired lip-readers.

The auto-mocking of those who are paid big bucks to offend the virtuous would be a long overdue civility-improving feedback loop.

I didn't write this. That's my story and I'm sticking to it. Someone else wrote it when I was away from my PC.
5 / 5 (2) Oct 28, 2008
I think this technology is already in use in non-commercial circles so I guess it was only a matter of time before it was made commercial.

Am I offended? YES.

I saw a speech by Osama Bin Laden that may have been created using this software.

My points here is. Can anything you see someone say and hear someone say actually be believed?

How do we know they said or did what we saw them say or do?
4 / 5 (1) Oct 29, 2008
Who was it that said: "believe nothing of what you read and half of what you see."
not rated yet Oct 29, 2008
This is absolutely despicable that they are even thinking of this. I guess the Chinese and some fundamentalists in the US are the launch customers. Who decides what is offensive? Guess the media will sound like those sanitised airline movies that are so extremely sensored. We seem to accept that our freedom is slowly taken away not only from governments but also from corporations.
not rated yet Nov 01, 2008
Such a system would work between adults by allowing the receiver to opt in for the censored words, while opting out the children from those words. It would need a networked feed into the reciver brain as a digital stream, opposed to sound waves as the communication method. For me to accept it there would need to a certification of stream authenticity. I fear that without a standards this could be used to manipulate the general population. Why stop with audio? The next technology could be a program to manipulate the persons mouth into speaking the words on a television broadcast. Fear not the technoloy as it is enivitable, instead work on the rules and law for it's application.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.