| 摘要 |
The speech control unit ( 100 ) comprises: a microphone array, comprising multiple microphones ( 102, 104, 106, 108 and 110 ) for receiving respective audio signals ( 103, 105, 107, 109 and 111 ); abeam forming module ( 116 ) for extracting a clean, i.e. speech, signal ( 117 ) of a user (U 1 ), from the audio signals; a keyword recognition system ( 120 ) for recognition of a predetermined keyword that is spoken by the user (U 1 ) and which is represented by a particular audio signal ( 111 ) and being arranged to control the beam forming module, on basis of tie recognition; and a speech recognition unit ( 118 ) for creating an instruction for the apparatus ( 200 ) based on recognized speech items of the speech signal ( 117 ). As a consequence, the speech control unit ( 100 ) is more selective for those parts of the audio signals for speech recognition which correspond to speech items spoken by the user (U 1 ).
|
