# Residual Convolutional CTC Networks for Automatic Speech Recognition

arXiv: https://arxiv.org/abs/1702.07793 · HTML: https://mlsanity.com/paper/1702.07793/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2017.

## Built on by (most cited first, 21 of 21)

- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better](https://mlsanity.com/paper/2108.07969/) (2021)
- [Improving Adversarial Robustness via Channel-wise Activation Suppressing](https://mlsanity.com/paper/2103.08307/) (2021)
- [Self-Ensemble Adversarial Training for Improved Robustness](https://mlsanity.com/paper/2203.09678/) (2022)
- [Robust Weight Perturbation for Adversarial Training](https://mlsanity.com/paper/2205.14826/) (2022)
- [Generalist: Decoupling Natural and Robust Generalization](https://mlsanity.com/paper/2303.13813/) (2023)
- [Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training](https://mlsanity.com/paper/2312.07067/) (2023)
- [What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space](https://mlsanity.com/paper/2101.06898/) (2021)
- [Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression](https://mlsanity.com/paper/2102.02950/) (2021)
- [On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization](https://mlsanity.com/paper/2212.09082/) (2022)
- [Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge](https://mlsanity.com/paper/2409.01627/) (2024)
- [Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training](https://mlsanity.com/paper/2106.05453/) (2021)
- [Clustering Effect of (Linearized) Adversarial Robust Models](https://mlsanity.com/paper/2111.12922/) (2021)
- [Strength-Adaptive Adversarial Training](https://mlsanity.com/paper/2210.01288/) (2022)
- [On Creating A Brain-To-Text Decoder](https://mlsanity.com/paper/2501.06326/) (2025)
- [Distribution-restrained Softmax Loss for the Model Robustness](https://mlsanity.com/paper/2303.12363/) (2023)
- [Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model](https://mlsanity.com/paper/2406.03409/) (2024)
- [Brightness-Restricted Adversarial Attack Patch](https://mlsanity.com/paper/2307.00421/) (2023)
- [CIARD: Cyclic Iterative Adversarial Robustness Distillation](https://mlsanity.com/paper/2509.12633/) (2025)
- [Voice Quality and Pitch Features in Transformer-Based Speech Recognition](https://mlsanity.com/paper/2112.11391/) (2021)
- [Patch Synthesis for Property Repair of Deep Neural Networks](https://mlsanity.com/paper/2404.01642/) (2024)

## Abstract (arXiv)

Deep learning approaches have been widely used in Automatic Speech Recognition (ASR) and they have achieved a significant accuracy improvement. Especially, Convolutional Neural Networks (CNNs) have been revisited in ASR recently. However, most CNNs used in existing work have less than 10 layers which may not be deep enough to capture all human speech signal information. In this paper, we propose a novel deep and wide CNN architecture denoted as RCNN-CTC, which has residual connections and Connectionist Temporal Classification (CTC) loss function. RCNN-CTC is an end-to-end system which can exploit temporal and spectral structures of speech signals simultaneously. Furthermore, we introduce a CTC-based system combination, which is different from the conventional frame-wise senone-based one. The basic subsystems adopted in the combination are different types and thus mutually complementary to each other. Experimental results show that our proposed single system RCNN-CTC can achieve the lowest word error rate (WER) on WSJ and Tencent Chat data sets, compared to several widely used neural network systems in ASR. In addition, the proposed system combination can offer a further error reduction on these two data sets, resulting in relative WER reductions of 14.91% and 6.52% on WSJ dev93 and Tencent Chat data sets respectively.