# Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition

arXiv: https://arxiv.org/abs/2112.10108 · HTML: https://mlsanity.com/paper/2112.10108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 19 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Theano: A Python framework for fast computation of mathematical expressions](https://mlsanity.com/paper/1605.02688/) (2016)
- [The Microsoft 2017 Conversational Speech Recognition System](https://mlsanity.com/paper/1708.06073/) (2017)
- [Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition](https://mlsanity.com/paper/1807.11284/) (2018)
- [Very Deep Convolutional Neural Networks for Robust Speech Recognition](https://mlsanity.com/paper/1610.00277/) (2016)
- [Densely Connected Convolutional Networks for Speech Recognition](https://mlsanity.com/paper/1808.03570/) (2018)
- [Kaldi+PDNN: Building DNN-based ASR Systems with Kaldi and PDNN](https://mlsanity.com/paper/1401.6984/) (2014)

## Abstract (arXiv)

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.