Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition
This work addresses noise robustness in speech recognition, which is an incremental improvement for applications in noisy environments.
The paper tackled noise robust speech recognition by investigating densely connected convolutional networks (DenseNets) with domain adversarial training, finding that DenseNets are more robust against noise than other neural network models and that domain adversarial learning further improves robustness under known and unknown noise conditions.
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.