| 摘要 |
Voice command operated systems are being installed in modern motor vehicles with increasing frequency. Such systems should be operable by various vehicle occupants and from various seating positions. A new type of speech recognition system is described, which is good at accomplishing these tasks. Therein, for regulating the speech recognition system, the reception characteristic of a a directionally selective microphone array (12) is controlled by an optimization unit (10). These speech signals are then processed in a speech recognizer (11) at least parallel in time. Then, on the basis of the results provided by the speech recognizer (11), the reception characteristic of the microphone array (12) is so controlled by an optimization unit (10), that the recognition performance of the speech recognizer (11) downstream of the optimization unit (10) is optimized. Herein, the speech recognizer is supplied with the received speech signals from different spatial directions parallel or at least quasi-parallel via the speech channels (14), so that this selects and further processes those speech signals that have the potential for the best possible recognition performance. On the basis of the recognition results, the optimization unit (10) obtains via the speech recognizer the necessary regulatory signals (18), in order to optimize the reception characteristics of the microphone array (12) by means of the optimization unit (10) with regard to the respective direction from which speech signals are received, which have the potential for the best possible recognition performance.
|
