| 摘要 |
Various embodiments of systems and methods for reducing audio noise are disclosed. One or more sound components such as noise (154, 156) and network tone (158) can be detected based on power spectrum (152) obtained from a time-domain signal (142). Results of such detection can be used to make decisions (162) in determination of an adjustment spectrum (164, 166) that can be applied to the power spectrum. The adjusted power spectrum can be transformed back into a time-domain signal (172) that substantially removes undesirable noise(s) and/or accounts for known sound components such as the network tone.
|
