Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Constructing Family Trees of Multilingual Speech Using Gaussian Mixture Models

Shuichi Itahashi (1), Shiwei Zhu (2), Mikio Yamamoto (2)

(1) AIST, Japan; (2) University of Tsukuba, Japan

This paper proposes a method for automatically clustering multilingual speech so as to derive language family trees. We consider that the language is the source of information which generates speech feature parameters; the probability or statistical characteristics of this information is modeled by Gaussian mixture models (GMMs); then a distance measure between the GMMs is introduced. Based on this, we construct family trees of multilingual speech which are quite similar to those considered in linguistics.

Full Paper

Bibliographic reference.  Itahashi, Shuichi / Zhu, Shiwei / Yamamoto, Mikio (2005): "Constructing family trees of multilingual speech using Gaussian mixture models", In INTERSPEECH-2005, 2253-2256.