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

3 Jul 2017  ·  Jayadev Billa ·

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. read more

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here