Skip to main content
. Author manuscript; available in PMC: 2018 Feb 8.
Published in final edited form as: Proc IEEE Int Conf Acoust Speech Signal Process. 2017 Jun 19;2017:246–250. doi: 10.1109/ICASSP.2017.7952155

Fig. 3.

Fig. 3

Location of attractor points in the embedding space. Each dot corresponds to one of the 10000 mixtures sounds, visualized using the first three principal components. Two distinct attractor pairs are visible (denoted by A1 and A2).