The Gini index of speech

Scott Rickard, Maurice Fallon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In which representation is speech most sparse? Time-scale? Time-frequency? Which window generator and length should be used to create the sparsest decomposition? To answer these questions, we propose the Gini index, which is twice the area between the Lorenz curve and the 45 degree line, as a measure of signal sparsity. The Gini index, introduced in 1912, is one of the most common measures of income or wealth distribution and is used to measure the inequity, or sparseness, of wealth distribution. Numerous decompositions of the speech signals in the TIMIT database are used to determine the most sparse standard representation for speech.
Original languageEnglish
Title of host publicationProceedings of the 38th Conference on Information Science and Systems (CISS’04)
Number of pages5
Publication statusPublished - Mar 2004

Fingerprint Dive into the research topics of 'The Gini index of speech'. Together they form a unique fingerprint.

Cite this