Skip to main content
. 2017 Jun 23;141(6):4705–4714. doi: 10.1121/1.4986931

FIG. 7.

FIG. 7.

Comparison of speaker-set-dependent models (trained on 77 speakers and tested on six seen speakers) and speaker-dependent models in terms of STOI. Group means and standard errors are shown. (a) Performance with the unseen babble noise. (b) Performance with the unseen cafeteria noise.