Learning Deep Embedding with Acoustic and Phoneme Features for Speaker Recognition in FM Broadcasting

<div>Visualization of deep speaker embedding descriptors learned from two networks. The first 20 speakers (#10270–#10289) and some of their speech utterances are used for visualization.</div>

IET Biometrics

fig3

Figure 3

Figure 3: Learning Deep Embedding with Acoustic and Phoneme Features for Speaker Recognition in FM Broadcasting 