| | |
Summary: REDUCING F0 FRAME ERROR OF F0 TRACKING ALGORITHMS UNDER NOISY
CONDITIONS WITH AN UNVOICED/VOICED CLASSIFICATION FRONTEND
Wei Chu, Abeer Alwan
Department of Electrical Engineering
University of California, Los Angeles
Los Angeles, 90024
{weichu, alwan}@ee.ucla.edu
ABSTRACT
In this paper, we propose an F0 Frame Error (FFE) metric which
combines Gross Pitch Error (GPE) and Voicing Decision Error
(VDE) to objectively evaluate the performance of fundamental fre-
quency (F0) tracking methods. A GPE-VDE curve is then developed
to show the trade-off between GPE and VDE. In addition, we intro-
duce a model-based Unvoiced/Voiced (U/V) classification frontend
which can be used by any F0 tracking algorithm. In the U/V classi-
fication, we train speaker independent U/V models, and then adapt
them to speaker dependent models in an unsupervised fashion. The
U/V classification result is taken as a mask for F0 tracking. Exper-
iments using the KEELE corpus with additive noise show that our
statistically-based U/V classifier can reduce VDE and FFE for the
|
