# Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition

arXiv: https://arxiv.org/abs/1711.05448 · HTML: https://mlsanity.com/paper/1711.05448/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

## Built on by (most cited first, 9 of 9)

- [Domain-aware Neural Language Models for Speech Recognition](https://mlsanity.com/paper/2101.03229/) (2021)
- [A Parallelizable Lattice Rescoring Strategy with Neural Language Models](https://mlsanity.com/paper/2103.05081/) (2021)
- [Personalized Predictive ASR for Latency Reduction in Voice Assistants](https://mlsanity.com/paper/2305.13794/) (2023)
- [Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library](https://mlsanity.com/paper/2404.18722/) (2024)
- [Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition](https://mlsanity.com/paper/2111.08400/) (2021)
- [On Sampling-Based Training Criteria for Neural Language Modeling](https://mlsanity.com/paper/2104.10507/) (2021)
- [Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring](https://mlsanity.com/paper/2310.09680/) (2023)
- [Self-Normalized Importance Sampling for Neural Language Modeling](https://mlsanity.com/paper/2111.06310/) (2021)
- [Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models](https://mlsanity.com/paper/2312.12764/) (2023)

## Abstract (arXiv)

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.