Siemens Aktiengesellschaft

Bernhard K&auml;mmerer

Christoph Maggioni

In order to recognize a keyword in spoken speech, the keyword is subdivided, just like a test pattern to be recognized, into segments. The individual segments of the keyword and of the test pattern are mapped onto one another and a comparison measurement is made and is accumulated over the segments. The keyword is repeatedly stored in a training phase, a plurality of reference features respectively being determined for each segment of the keyword are stored. During recognition, a reference feature wich best fits the relevant segment of the test pattern is assigned in a segment-wise fashion.

Method and device for recognizing at least one keyword in spoken speech using a computer

The arrangement detects an object that is irradiated by waves in the invisible spectral range. Infrared illumination is preferably employed in order to recognize an object on a display projected onto an arbitrary surface that is displayed for the user in the visible spectral range and to be able to track the movement of this object. User interfaces produced by a computer can thus be projected onto an arbitrary background. Touch-free inputs can ensue on these user interfaces by moving the hand or with some other input unit, whereby the triggering of an action is coupled to a dwell for a prescribable time over a field linked to a control characteristic.

Growing community of inventors

Ottobrunn, Germany

Bernhard Kämmerer

Growing community of inventors

Ottobrunn, Germany

Bernhard K&auml;mmerer

Bernhard Kämmerer