Voice Signal Enhancement For Head-Worn Audio Devices

A method of voice signal enhancement based on a plurality of microphone signals of a plurality of microphones, the method comprising

• directivity pre-processing of the plurality of microphone signals to obtain at least a voice signal and a noise signal using microphone information of at least one of the plurality of microphones;
• and
• conducting blind source separation on at least the voice signal and the noise signal to obtain at least an enhanced voice signal with reduced noise components.

A head-worn audio device having a circuit for voice signal enhancement, the circuit comprising at least

• a plurality of microphones, arranged at predefined positions, where each microphone provides a microphone signal;
• a directivity pre-processor, connected with the plurality of microphones to receive the microphone signals and configured to provide at least a voice signal and a noise signal;
• a BSS processor, connected with the directivity pre-processor to receive at least the voice signal and the noise signal, and being configured to conduct blind source separation on at least the voice signal and the noise signal to provide at least an enhanced voice signal with reduced noise components.