论文标题
进化算法增强神经体系结构搜索与文本无关的扬声器验证
Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification
论文作者
论文摘要
最先进的演讲者验证模型基于深度学习技术，在很大程度上取决于专家或工程师的手工设计的神经体系结构。我们借用神经体系结构搜索（NAS）的概念，用于与文本无关的说话者验证任务。由于NAS可以自动学习深层的网络结构，因此我们将NAS概念引入众所周知的X-Vector网络。此外，本文提出了一种进化算法增强的神经体系结构搜索方法，称为自动向量，以自动发现有前途的网络，以实现扬声器验证任务。实验结果表明，我们基于NAS的模型优于最先进的说话者验证模型。
State-of-the-art speaker verification models are based on deep learning techniques, which heavily depend on the handdesigned neural architectures from experts or engineers. We borrow the idea of neural architecture search(NAS) for the textindependent speaker verification task. As NAS can learn deep network structures automatically, we introduce the NAS conception into the well-known x-vector network. Furthermore, this paper proposes an evolutionary algorithm enhanced neural architecture search method called Auto-Vector to automatically discover promising networks for the speaker verification task. The experimental results demonstrate our NAS-based model outperforms state-of-the-art speaker verification models.
