摘要 |
A method and system for removing acoustic noise removal (Fig. 5) from human speech is described. Acoustic noise is removed regardless of noise type, amplitude, or orientation. The system includes a processor (30) coupled among microphones (1, 2) and a voice activation detection ("V AD") element (104). The processor executes denoising algorithms that generate transfer functions. The processor (30) receives acoustic data from the microphones (1, 2) and data from the VAD (104) indicates voicing activity and when the VAD indicates no voicing activity. The transfer functions are used to generate a denoised data stream. |