Microsoft Patents Audio Stream Censorship Technology


Microsoft has been granted a patent on technology for censoring audio streams in real-time, which could bring an end to those unpleasant online experiences with foul-mouthed f********s.

Microsoft originally filed for the patent in October 2004, according to an Ars Technica report, describing it as as “automatic censoring filter employing 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 technology in question will presumably have applications far beyond just online gaming. Censorship of live television or radio will be considerably simplified, allowing for the elimination of live censors and broadcast delays, as will the imposition of censorship in areas where it has previously been impractical. “Humans are remarkably adept at identifying words and phrases that are considered unacceptable,” the approved patent says. “However, 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.”

I’ve always found carpet-f-bombing an amusing part of the online experience, but obviously not everyone is going to feel the same way about it. Microsoft hasn’t yet offered any details about how this technology will work, although the patent does describe an adjustable “probability threshold” that will increase or decrease the software’s sensitivity to naughty words. As long as the technology can be controlled independently, or turned off entirely, by the end user, I think it’ll be a real boon to online gaming. But I also have a vague concern that it could be used to impose choices rather than enable them. As the author of the Ars report, Jonathan Gitlin, wrote, “Think how valuable such a system might be to an authoritarian regime. As we’ve seen to good effect in Burma and elsewhere, the ubiquity of cell phones has been a good thing for dissidents who need to get their message out or organize themselves. The Great Firewall of China already blocks objectionable web content from reaching Chinese computers; what’s to stop cell phones from censoring anti-government conversations too?”

About the author