# Fully Convolutional Speech Recognition

arXiv: https://arxiv.org/abs/1812.06864 · HTML: https://mlsanity.com/paper/1812.06864/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2018.

## Built on by (most cited first, 19 of 19)

- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Towards End-to-end Unsupervised Speech Recognition](https://mlsanity.com/paper/2204.02492/) (2022)
- [Learning strides in convolutional neural networks](https://mlsanity.com/paper/2202.01653/) (2022)
- [Pushing the Limits of Non-Autoregressive Speech Recognition](https://mlsanity.com/paper/2104.03416/) (2021)
- [A Parallelizable Lattice Rescoring Strategy with Neural Language Models](https://mlsanity.com/paper/2103.05081/) (2021)
- [ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems](https://mlsanity.com/paper/2102.08535/) (2021)
- [Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model](https://mlsanity.com/paper/2303.00091/) (2023)
- [DNArch: Learning Convolutional Neural Architectures by Backpropagation](https://mlsanity.com/paper/2302.05400/) (2023)
- [Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition](https://mlsanity.com/paper/2507.05724/) (2025)
- [Do End-to-End Speech Recognition Models Care About Context?](https://mlsanity.com/paper/2102.09928/) (2021)
- [And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?](https://mlsanity.com/paper/2210.01256/) (2022)
- [Deformable TDNN with adaptive receptive fields for speech recognition](https://mlsanity.com/paper/2104.14791/) (2021)
- [Back from the future: bidirectional CTC decoding using future information in speech recognition](https://mlsanity.com/paper/2110.03326/) (2021)
- [BEA-Base: A Benchmark for ASR of Spontaneous Hungarian](https://mlsanity.com/paper/2202.00601/) (2022)
- [Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition](https://mlsanity.com/paper/2209.15176/) (2022)
- [Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions](https://mlsanity.com/paper/2501.13230/) (2025)
- [Voice Quality and Pitch Features in Transformer-Based Speech Recognition](https://mlsanity.com/paper/2112.11391/) (2021)

## Abstract (arXiv)

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we present an alternative approach based solely on convolutional neural networks, leveraging recent advances in acoustic models from the raw waveform and language modeling. This fully convolutional approach is trained end-to-end to predict characters from the raw waveform, removing the feature extraction step altogether. An external convolutional language model is used to decode words. On Wall Street Journal, our model matches the current state-of-the-art. On Librispeech, we report state-of-the-art performance among end-to-end models, including Deep Speech 2 trained with 12 times more acoustic data and significantly more linguistic data.