作者: Wei Zhang , S. Gazor
DOI: 10.1109/ICOSP.2002.1181096
关键词:
摘要: The Gaussian and Laplacian models of speech signals are investigated in this paper. We use different hypothesis tests to compare these two models. model has been widely used while our experimental results show that the probability density functions (PDFs) more like distributions. Based on fact KLT DCT have excessively signal processing, distribution components both decorrelated domains also investigated. All illustrate follow distributions time domain samples or (excluding DC) domains. uncorrelated can be assumed as a multivariate Laplacian.