TL;DR本文提出 Global Filter for TDNN 和 Dual-Stream TDNN 模型,可在语音辨识方面取得显著的效果,同时减少了参数和复杂性。
Abstract
The time-delay neural network (TDNN) is one of the state-of-the-art models
for text-independent speaker verification. However, it is difficult for
conventional TDNN to capture global context that has been proven