Skip to main content

Table 1 Details about the speakers and the sentences, including speakers and sentences ID, their genders, dialect regions (DR), used in training or test dataset and used as the target or interferers

From: Localization based stereo speech source separation using probabilistic time-frequency masking and deep neural networks

ID Sex DR Sentence ID Dataset Source type
TBR0 F 1 21 201 381 111 291 Training /
MEM0 F 1 297 333 207 387 117 Training /
BJK0 M 2 95 275 5 185 365 Testing Target
RMS1 M 7 407 137 317 47 227 Testing Target
CTT0 M 5 28 208 388 118 298 Testing Interferer 1
PKT0 F 3 8 188 368 98 278 Testing Interferer 1
BDG0 M 3 383 113 293 23 203 Testing Interferer 2
UTB0 F 5 124 304 34 214 394 Testing Interferer 2