| | |
Summary: AUTOMATIC ESTIMATION OF THE SECOND SUBGLOTTAL RESONANCE FROM
NATURAL SPEECH
Harish Arsikere Steven M. Lulich,
Abeer Alwan
Department of Electrical Engineering, University of California, Los Angeles
Department of Psychology, Washington University, Saint Louis
Department of Speech and Hearing Sciences, Indiana University, Bloomington
harishan@ucla.edu, slulich@wustl.edu, alwan@ee.ucla.edu
ABSTRACT
This paper deals with the automatic estimation of the second subglot-
tal resonance (Sg2) from natural speech spoken by adults, since our
previous work focused only on estimating Sg2 from isolated diph-
thongs. A new database comprising speech and subglottal data of na-
tive American English (AE) speakers and bilingual Spanish/English
speakers was used for the analysis. Data from 11 speakers (6 females
and 5 males) were used to derive an empirical relation among the
second and third formant frequencies (F2 and F3) and Sg2. Using
the derived relation, Sg2 was automatically estimated from voiced
|
