Title: Spoken Language Identification by Means of Acosutic Mid-level Descriptors
Authors: Uwe D. Reichel, Andreas Triantafyllopoulos, Christopher Oates, Stephan Huber, Björn Schuller
Abstract:
We introduce an acoustic mid-level feature (MLD) set derived from
openSMILE low-level descriptors for the purpose of language characterisation and
identification. The four languages targeted in this study are Georgian, Pashto, Kurmanji
Kurdish, and Turkish. Language-dependent differences of these features will
be discussed in terms of language typology. Furthermore, language identification
by feed forward neural networks is comparatively evaluated for the MLDs and for
openSMILE functionals, as well as for varying segment of analysis lengths. The
best result 76.3% UAR was achieved for a joint feature set and for a minimum
speech chunk length of 8 seconds.
Year: 2020
In session: Acoustic Signals
Pages: 125 to 132