# Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions

arXiv: https://arxiv.org/abs/2010.07597 · HTML: https://mlsanity.com/paper/2010.07597/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild](https://mlsanity.com/paper/2106.03932/) (2021)
- [Speech recognition for air traffic control via feature learning and end-to-end training](https://mlsanity.com/paper/2111.02654/) (2021)
- [Graph in Graph Neural Network](https://mlsanity.com/paper/2407.00696/) (2024)

## Abstract (arXiv)

Many end-to-end Automatic Speech Recognition (ASR) systems still rely on pre-processed frequency-domain features that are handcrafted to emulate the human hearing. Our work is motivated by recent advances in integrated learnable feature extraction. For this, we propose Lightweight Sinc-Convolutions (LSC) that integrate Sinc-convolutions with depthwise convolutions as a low-parameter machine-learnable feature extraction for end-to-end ASR systems. We integrated LSC into the hybrid CTC/attention architecture for evaluation. The resulting end-to-end model shows smooth convergence behaviour that is further improved by applying SpecAugment in time-domain. We also discuss filter-level improvements, such as using log-compression as activation function. Our model achieves a word error rate of 10.7% on the TEDlium v2 test dataset, surpassing the corresponding architecture with log-mel filterbank features by an absolute 1.9%, but only has 21% of its model size.