| CPC H04B 1/1081 (2013.01) [H04B 1/1027 (2013.01)] | 20 Claims |

|
1. A method for assessing a noise reduction algorithm and subsequent training of a neural network comprising the steps of:
providing a spectrogram containing noise and at least one signal of interest to the neural network;
analyzing the spectrogram to create a transfer function for a noise reduction algorithm;
applying the noise reduction algorithm to the spectrogram to produce a noise reduced spectrogram;
identifying a signal of interest within the noise reduced spectrogram;
calculating an assessment criterion for the noise reduced spectrogram or the signal of interest; and
iteratively creating an updated transfer function based on a value of the assessment criteria.
|