Michael Picheny - Spoken Term Detection - A Loss for Words

As speech recognition continues to improve, new applications of the technology have been enabled. It is now common to search for information and send accurate short messages by speaking into a cellphone - something completely impractical just a few years ago. Another application that has recently been gaining attention is "Spoken Term Detection" - using speech recognition technology to locate key words or phrases of interest in running speech of variable quality. Spoken Term Detection can be used to issue real time alerts, rapidly identify multimedia clips of interesting content, and, when combined with search technology, even provide real-time commentary during broadcasts and meetings. This talk will describe the basics of Spoken Term Detection systems, including recent advances in core speech recognition technology, performance metrics, how out-of-vocabulary queries are handled, and ways of using score normalization and system combination to dramatically improve system performance.