Dropout Approaches for LSTM Based Speech Recognition Systems

Jayadev Billa

ICASSP 2018accepted0 citations

Dropout Approaches for LSTM Based Speech Recognition Systems

Abstract

In this paper we examine dropout approaches in a Long Short Term Memory (LSTM) based automatic speech recognition (ASR) system trained with the Connectionist Temporal Classification (CTC) loss function. In particular, using an Eesen based LSTM-CTC speech recognition system, we present dropout implementations that result in significant improvements in speech recognizer performance on Librispeech and GALE Arabic datasets, with 24.64% and 13.75% relative reduction in word error rates (WER) from their respective baselines.

BibTeX

@inproceedings{icassp2018_dropoutapproache,
  title = {Dropout Approaches for LSTM Based Speech Recognition Systems},
  author = {Jayadev Billa},
  booktitle = {ICASSP 2018},
  year = {2018}
}