# Exploring End-to-End Techniques for Low-Resource Speech Recognition

arXiv: https://arxiv.org/abs/1807.00868 · HTML: https://mlsanity.com/paper/1807.00868/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 1 of 1)

- [Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition](https://mlsanity.com/paper/2103.07186/) (2021)

## Abstract (arXiv)

In this work we present simple grapheme-based system for low-resource speech recognition using Babel data for Turkish spontaneous speech (80 hours). We have investigated different neural network architectures performance, including fully-convolutional, recurrent and ResNet with GRU. Different features and normalization techniques are compared as well. We also proposed CTC-loss modification using segmentation during training, which leads to improvement while decoding with small beam size. Our best model achieved word error rate of 45.8%, which is the best reported result for end-to-end systems using in-domain data for this task, according to our knowledge.