Densely Connected Convolutional Networks for Speech Recognition

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseNets are very deep, compact convolutional neural networks, which have demonstrated incredible improvements over the state-of-the-art results on several data sets in computer vision. Our experimental results show that DenseNet can be used for AM significantly outperforming other neuralbased models such as DNNs, CNNs, VGGs. Furthermore, results onWall Street Journal revealed that with only a half of the training data DenseNet was able to outperform other models trained with the full data set by a large margin.