What The @#*$? Microsoft Patents Audio Speech Censorship.
An input audio data stream comprising speech is processed by an automatic censoring filter in either a real-time mode, or a batch mode, producing censored speech that has been altered so that undesired words or phrases are either unintelligible or inaudible. 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.
The patent uses methods for muting offensive words and replacing them with bleeping or using alternative words. For example when playing Halo, people can swear at each other over wireless headsets. I’m sure that those with kids don’t want their young ones to be sworn at. This is possibly one of Microsoft’s ways of preventing this from happening.
Below is a process model of how the patent would work in action (pulled from the patent documentation):