摘要 |
The present invention relates to a system for speech signal processing with noise reduction, comprising a microphone array comprising at least two microphones to detect microphone signals, a pre-processing means connected to the microphone array to receive microphone signals comprising means configured to perform a time delay compensation of the microphone signals to obtain pre-processed signals, a first signal processing means connected to the pre-processing means to receive the pre-processed signals comprising a means configured to generate at least one noise reference signal, in particular, one noise reference signal for each microphone signal, second signal processing means connected to the pre-processing means to receive the pre-processed signals comprising an adaptive beam former to obtain a beamformed signal, and an adaptive noise cancelling means configured to reduce noise of the beamformed signal on the basis of the at least one noise reference signal.
|