TL;DR本文提出了一种去噪深度神经网络 (DDNN) 声活检测 (VAD) 方法,通过无监督预训练的方式提取特征并通过监督学习修正,实验结果表明该方法优于基于深度置信网络 (DBN) 的 VAD 并且在深度层次上具有明显优势。
Abstract
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD)
has been proposed. It is powerful in fusing the advantages of multiple
features, and achieves the state-of-the-art performance. Howeve