ADAPTIVE AUDIO FRAME PROCESSING FOR KEYWORD DETECTION

摘要

A method of detecting a target keyword from an input sound for activating a function in a mobile device is disclosed. In this method sound features are extracted from the input stream and statistics are generated (340) including the mean value and the variance of a particular sound feature. Based on the statistics the method adaptively skips the normalisation of a sound feature when the difference between the present value and the previous value is not significant, this has the effect of lowering the process load. In detail a first plurality of sound features is received in a buffer (330), and a second plurality of sound features is received in the buffer 330). While receiving each of the second plurality of sound features in the buffer, a first number of the sound features are processed from the buffer. The first number of the sound features includes two or more sound features. Further, the method includes determining a keyword score (360) for each of the processed sound features and detecting the input sound as the target keyword (370) if at least one of the keyword scores is greater than a threshold score.