Everybody keeps talking about Siri, and for a good reason. Since it is clearly the market state-of-the-art in speech understanding, we set out to measure our own fundamental semantic abilities against Siri’s high bar. Admittedly, our work is still a prototype, so the focus here was on core technology as opposed to product polish. The results were … quite stimulating. Here is the first one in the series of experiments. You be the judge!
