We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. DenseNets are very deep, compact convolutional neural networks which have demonstrated incredible improvements over the state-of-the-art results in computer vision. Our experimental results reveal that DenseNets are more robust against noise than other neural network based models such as deep feed forward neural networks and convolutional neural networks. Moreover, domain adversarial learning can further improve the robustness of DenseNets against both, known and unknown noise conditions.
翻译:我们调查了紧密连通的革命网络(DenseNets)及其与域对称培训的延伸,以获得噪音强力语音识别。 DenseNets是非常深入的、紧凑的进化神经网络,这些网络在计算机视觉方面的先进成果上已经表现出令人难以置信的改善。 我们的实验结果表明,DenseNet比其他神经网络模型(如深植的前神经网络和进化神经网络)更能抵御噪音。 此外,域对称学习可以进一步提高DencyNet对已知和未知噪音条件的强大性。