ODYSSEY 2004 - The Speaker and Language Recognition Workshop
May 31 - June 3, 2004
Recent studies have indicated that language identity is encapsulated in a more complicated manner to that represented by short term acoustic features. In particular, trajectory information over syllable-like durations have shown significant promise. This study introduces a novel three-tiered language identification approach which incorporates this information as well as acoustic context in the form of broad syllabic events. Experimental results using the CallFriend database demonstrate the effectiveness of these systems at providing complementary information to a GMM based system.
Bibliographic reference. Martin, Terrence / Wong, Eddie / Baker, Brendan / Mason, Michael / Sridharan, Sridha (2004): "Pitch and energy trajectory modelling in a syllable length temporal framework for language identification", In ODYS-2004, 289-296.