Time delay neural network (TDNN) has been proven to be efficient in learning discriminative speaker embeddings. One of its successful variant, ECAPA-TDNN, achieved state-of-the-art performance on speaker verification tasks at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses densely connected time delay neural network (D-TDNN) as backbone and adopts a novel multi-granularity pooling to capture contextual information at different levels. Extensive experiments on two public benchmarks, VoxCeleb and CN-Celeb, demonstrate that the proposed architecture outperforms other mainstream speaker verification systems with lower computational cost and faster inference speed.
翻译:事实证明,时间延迟神经网络(TDNN)在学习歧视性演讲者嵌入器方面是有效的。它的成功变体之一,即ECAPA-TDNNN,以计算复杂程度高得多和推推速慢得多的代价,实现了发言者核查任务方面的最先进的表现。这使得它不足以应对要求很高的推断率和有限计算资源的假设情况。因此,我们有兴趣找到一个能够实现ECAPA-TDNN和Vanilla TDNN效率的架构。在本文中,我们提议建立一个基于环境意识掩蔽的有效网络,即CAM++,利用密集连接的时间延迟神经网络(D-TDNNN)作为主干线,并采用新型的多语种集合,在不同级别捕捉背景信息。关于VoxCeleb和CN-Celeb这两个公共基准的广泛实验表明,拟议的结构比其他主流演讲者核查制度的计算成本低,推断速度更快。</s>