Synthesizing sound textures through wavelet tree learning

Shlomo Dubnov, Ziv Bar-Joseph, Ran El-Yaniv, Dani Lischinski, Michael Werman

Research output: Contribution to journalArticlepeer-review

61 Scopus citations


Natural sounds are complex phenomena which contain a mixture of events localized in time and frequency. As such, a statistical learning algorithm for synthesizing random instances of sound textures from an existing natural sound example is presented. It describes sound textures as a set of repeating structural elements subject to some randomness in their time appearance and relative ordering but preserving certain essential temporal coherence and across-scale localization.

Original languageEnglish
Pages (from-to)38-48
Number of pages11
JournalIEEE Computer Graphics and Applications
Issue number4
StatePublished - 1 Jul 2002

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Synthesizing sound textures through wavelet tree learning'. Together they form a unique fingerprint.

Cite this