Abstract: A method for acoustic echo cancellation is disclosed herein. A microphone receives a second acoustic signal from a near-end environment, the second acoustic signal including a delayed version of the first acoustic signal from a far-end environment. A processor models a relationship between the first acoustic signal and the second acoustic signal using an adaptive filter. The adaptive filter uses sampling points of the first acoustic signal and the second acoustic signal along a timeline as inputs. The processor identifies a sampling point among the sampling points, wherein weight values of the adaptive filter associated with the identified sampling point experience a significant increase (e.g., 50% increase). The identified sampling point along the timeline represents an estimated delay between the first acoustic signal and the second acoustic signal. The processor further removes the delayed version of the first acoustic signal from the second acoustic signal based on the estimated delay.

Abstract: A method for acoustic echo cancellation is disclosed herein. A microphone receives a second acoustic signal from a near-end environment, the second acoustic signal including a delayed version of the first acoustic signal from a far-end environment. A processor models a relationship between the first acoustic signal and the second acoustic signal using an adaptive filter. The adaptive filter uses sampling points of the first acoustic signal and the second acoustic signal along a timeline as inputs. The processor identifies a sampling point among the sampling points, wherein weight values of the adaptive filter associated with the identified sampling point experience a significant increase (e.g., 50% increase). The identified sampling point along the timeline represents an estimated delay between the first acoustic signal and the second acoustic signal. The processor further removes the delayed version of the first acoustic signal from the second acoustic signal based on the estimated delay.