A deep neural network based audio processing method is provided. The method includes: obtaining a deep neural network based speech extraction model; receiving an audio input object having a speech portion and a non-speech portion, wherein the audio input object includes one or more audio data frames each having a set of audio data samples sampled at a predetermined sampling interval and represented in time domain data format; obtaining a user audiogram and a set of user gain compensation coefficients associated with the user audiogram; and inputting the audio input object and the set of user gain compensation coefficients into the trained speech extraction model to obtain an audio output result represented in time domain data format outputted by the trained speech extraction model, wherein the non-speech portion of the audio input object is at least partially attenuated in or removed from the audio output result.