Gamertell

Back in 2004, Microsoft filed a patent for real-time speech technology and, four years later, the patent has been approved, reports Ars Technica.

If you, like me, are wondering exactly how this technology works, that’s where 1UP went ahead and dug deep into the patent itself and pulled out a rather detailed description:

“The automatic censoring filter employs a lattice comprising either phonemes and/or words derived from phonemes for comparison against corresponding phonemes or words included in undesired speech data. If the probability that a phoneme or word in the input audio data stream matches a corresponding phoneme or word in the undesired speech data is greater than a probability threshold, the input audio data stream is altered so that the undesired word or a phrase comprising a plurality of such words is unintelligible or inaudible. The censored speech can either be stored or made available to an audience in real-time.”

Even further down into the patent is where 1UP found the part specifically tailored to online chatting:

“For certain types of broadcasts, it would be preferable to employ a more automated approach that avoids the need to pay for or provide a human censor to monitor the broadcast, while still enabling the audio data to be censored at an appropriate level. For example, in massive multiplayer games, it would be impractical to employ a human censor to monitor the multitude of voice chat sessions that might be occurring at one time.”

In a nutshell, if developed, the tech could automatically censor naughty words. As every Xbox Live player knows of the horror, er, stupidity that is caused by the famous Penny Arcade theory: Internet + Anonymity = Jerks. It’s a problem Xbox Live has struggled with, YouTube has exploited and parents have called customer service in frantic terror and blind rage over. If it works, the tech would diminish the Jerk side of the equation.

Of course, this technology would have to work rather quickly in order to intercept all the naughty vocals and as anyone who plays online is already aware, speech is instant. So how exactly would this technology instant intercept the bad words? Would this mean a delay in the chat? Further more, as 1UP mentions, what if someone spoke incoherently? Would this new technology be able to accurately pick out the right rights? Would it censor non-bad words like, as 1UP so colorfully mentions, the word funk?

Granted there is still a lot of theorizing and testing for this technology and we probably won’t see it appear for a couple years. But when we do, how is this going to be implemented in videogames? Optional filters? Will it play a nice beeping sound to cover up the bad words or will it take the Bionic Commando Podcast approach of putting silly-like sounding words in? Will this change ESRB ratings? How does this conflict with our First Amendment rights to free speech?

Lots of questions to be answered. So how do you guys feel about this? Does this censoring technology not matter to you at all? Let us know in the comment section below. 

Read [Ars Technica] Via [1UP]

Image borrowed from Penny Arcade.