EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Average intelligibility scores ${\bar{C}}_{A}$ , ${\bar{C}}_{N}$ , and ${\bar{C}}_{S}$ , and the average relative visual contribution ${\bar{C}}_{V}$ of the animated avatar driven by speech, for three different SNRs

From: A comprehensive system for facial animation of generic 3D head models driven by speech

	${\bar{C}}_{A}$	${\bar{C}}_{N}$	${\bar{C}}_{S}$	${\bar{C}}_{V}$
-10 dB	0.5704	0.8426	0.7407	0.7628
-15 dB	0.4852	0.7944	0.6796	0.7770
-20 dB	0.3704	0.7389	0.5963	0.7735

Back to article page