We present a new method for noisy speech recognition, which combines multiple timescale analysis with sub band method.

本文根据多时间尺度分析与子带方法，提出了一种多时间尺度复合子带的噪声环境下语音识别新方法。

youdao

Then, multifractal analysis is performed for low frequency sub-band. The multifractal spectrum is used as the characteristic parameters to filter pixels which mark different scenery.

然后对低频子带进行多重分形特性分析，再将多重分形谱作为特征参量进行像素筛选，筛选出标志不同景物的像素点。

youdao