# Improving LSTM-CTC based ASR performance in domains with limited training data

arXiv: https://arxiv.org/abs/1707.00722 · HTML: https://mlsanity.com/paper/1707.00722/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2017.

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

- [Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model](https://mlsanity.com/paper/2104.02558/) (2021)

## Abstract (arXiv)

This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connectionist temporal classification (CTC) loss function and systems based on hybrid Deep Neural Networks (DNNs) trained with the cross entropy (CE) loss function on domains with limited data. We step through a number of experiments that show incremental improvements on a baseline EESEN toolkit based LSTM-CTC ASR system trained on the Librispeech 100hr (train-clean-100) corpus. Our results show that with effective combination of data augmentation and regularization, a LSTM-CTC based system can exceed the performance of a strong Kaldi based baseline trained on the same data.