Method and device for timing alignment of audio signals

Abstract

A method and device for timing alignment of audio signals. The method includes: generating frequency domain images respectively for an audio signal to be aligned and a template audio signal (S); inputting the frequency domain images into a twin neural network of a timing offset prediction model respectively, to obtain two frequency domain features output by the twin neural network (S); fusing the two frequency domain features to obtain a fused feature (S); inputting the fused features into a prediction network of the timing offset prediction model to obtain a timing offset output by the prediction network (S); and performing timing alignment processing on the audio signal to be aligned according to the timing offset (S). The technical solution is more robust, and especially in a noisy environment, features extracted by a deep neural network are more intrinsic and more stable. An end-to-end timing offset prediction model is more accurate and faster.