摘要 |
<p>A speech signal (2) is subjected to vocal tract analysis and the output therefrom is analysed by a neural network (5). The output from the neural network is compared with the parameters stored in the network definition function (4), to derive measurement of the quality of the signal supplied to the source (2). The network definition function is determined by applying to the trainable processing apparatus a distortion perception measure indicative of the extent to which a distortion would be perceptible to a human listener.</p> |