I had the opportunity to attend Microsoft TechFest the other day – placing me smack dab in the middle of a researcher’s zeitgeist. One of the more interesting conversations I had was with Jasha Droppo – you have to see it to hear it to believe it. If you’ve ever dealt with background noise in audio and/or video files, you’ll really appreciate what Microsoft Research has developed.
From the patent:
A pattern recognition system, such as a speech recognition system, takes an input signal and attempts to decode the signal to find a pattern represented by the signal. For example, in a speech recognition system, a speech signal (often referred to as a test signal) is received by the recognition system and is decoded to identify a string of words represented by the speech signal.