论文标题
贝叶斯X-Vector：贝叶斯神经网络基于X-Vector的X-Vector系统，用于扬声器验证
Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
论文作者
论文摘要
说话者验证系统通常会遇到培训和评估数据之间的不匹配问题，例如说话者人口不匹配，渠道和环境变化。为了解决此问题，它要求系统对看不见的数据具有良好的概括能力。在这项工作中，我们将贝叶斯神经网络（BNN）纳入深神经网络（DNN）X-vector Speaker验证系统，以提高系统的概括能力。通过BNN提供的重量不确定性建模，我们希望系统可以更好地概括在评估数据上，并更准确地进行验证决策。我们的实验结果表明，DNN X-Vector系统可以从BNN中受益，尤其是在使用室外数据的评估严重的情况下，尤其是当不匹配问题严重时。具体而言，结果表明，该系统可以从BNN中受益于BNN，而对于短距离和长期性内域评估，该系统的相对降低分别为2.66％和2.32％。此外，DNN X-Vector和Bayesian X-Vector Systems的融合可以进一步改进。此外，通过室外评估进行的实验，例如在对NIST SRE10核心测试进行评估时，在Voxceleb1上训练的模型表明，BNN可以带来较大的相对EER降低约4.69％。
Speaker verification systems usually suffer from the mismatch problem between training and evaluation data, such as speaker population mismatch, the channel and environment variations. In order to address this issue, it requires the system to have good generalization ability on unseen data. In this work, we incorporate Bayesian neural networks (BNNs) into the deep neural network (DNN) x-vector speaker verification system to improve the system's generalization ability. With the weight uncertainty modeling provided by BNNs, we expect the system could generalize better on the evaluation data and make verification decisions more accurately. Our experiment results indicate that the DNN x-vector system could benefit from BNNs especially when the mismatch problem is severe for evaluations using out-of-domain data. Specifically, results show that the system could benefit from BNNs by a relative EER decrease of 2.66% and 2.32% respectively for short- and long-utterance in-domain evaluations. Additionally, the fusion of DNN x-vector and Bayesian x-vector systems could achieve further improvement. Moreover, experiments conducted by out-of-domain evaluations, e.g. models trained on Voxceleb1 while evaluated on NIST SRE10 core test, suggest that BNNs could bring a larger relative EER decrease of around 4.69%.
