Skip to main content
. Author manuscript; available in PMC: 2010 Feb 25.
Published in final edited form as: IEEE Trans Audio Speech Lang Process. 2006 Nov;14(6):2212–2221. doi: 10.1109/TASL.2006.872611

Fig. 4.

Fig. 4

Schematic representation of the estimation of glottal events for the target speaker. Events for the target sound (solid arrows) and background speech (dashed arrows) were first estimated from the compensated NAP. The target event (rightmost box) was estimated from the compensated NAP by cross-correlating with the triplet of Gaussians.