12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

A Real-Time Speech Command Detector for a Smart Control Room

Daniel Reich (1), Felix Putze (1), Dominic Heger (1), Joris Ijsselmuiden (2), Rainer Stiefelhagen (2), Tanja Schultz (1)

(1) KIT, Germany
(2) Fraunhofer IOSB, Germany

In this work we present an always-on speech recognition system that discriminates spoken commands directed to the system from other spoken input. For discrimination we integrated various features ranging from prosodic cues and decoding features to linguistic information. The resulting "Speech Command Detector" provides intuitive hands-free user interaction in a Smart Control Room environment where voice commands are directed toward a large interactive display. Based on a recognition vocabulary of 259 words with more than 10k possible commands, the Speech Command Detector detected 88.3% of the commands correctly maintaining a very low False Positive Rate of 1.5%. In a crossdomain setup the system was evaluated on a Star Trek episode. With only minor adjustments, our system achieved very promising results with 91.2% command detection rate at a False Positive Rate of 1.8%.

Full Paper

Bibliographic reference.  Reich, Daniel / Putze, Felix / Heger, Dominic / Ijsselmuiden, Joris / Stiefelhagen, Rainer / Schultz, Tanja (2011): "A real-time speech command detector for a smart control room", In INTERSPEECH-2011, 2641-2644.