The baseline system we used is text-independent speaker identification system.

所采用的基线系统为文本无关的说话人辨认系统。

youdao

In a speaker identification system, training speaker models is computationally expensive, especially when the dimension of feature vectors is large.

在说话人识别系统中，通常训练说话人模型需要很长的时间，特别当说话人特征的维数很高时。

youdao

The background noise leads a mismatch between the training environment and testing environment, and degrades the performance of speaker identification system.

背景噪声的存在，使得说话人识别系统的训练环境和测试环境发生失配，导致系统性能发生急剧下降。

youdao