Lattice rescoring strategies for long short term memory language models in speech recognition

Shankar Kumar, Michael Nirschl, Daniel Holtmann-Rice, Hank Liao, Ananda Theertha Suresh, Felix Yu

Abstract

Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with new variants on a YouTube speech recognition task. Lattice rescoring using LSTMLMs reduces the word error rate (WER) for this task by 8% relative to the WER obtained using an N-gram LM.

Locations

• arXiv (Cornell University) - View - PDF
• 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) - View