Methods and systems for enhancing signal quality are disclosed. A method includes receiving buffers of sound samples including a first microphone signal and a second microphone signal from a first and a second microphone; generating a first cardioid shape signal by subtracting a delayed second microphone signal from the first microphone signal; generating a second cardioid shape signal by subtracting the second microphone signal from a delayed first microphone signal; generating a first level output signal based on the first cardioid shape signal; detecting at least one speech and non-speech region of the first level output signal; generating a second level output signal based on the second cardioid shape signal, and at least one of the speech and non-speech regions of the first level output signal; and removing residuals of noise from the first level output signal based on adaptive weights output and generated second level output signal.