# LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring

arXiv: https://arxiv.org/abs/1907.01030 · HTML: https://mlsanity.com/paper/1907.01030/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Conformer-based Hybrid ASR System for Switchboard Dataset](https://mlsanity.com/paper/2111.03442/) (2021)
- [A Parallelizable Lattice Rescoring Strategy with Neural Language Models](https://mlsanity.com/paper/2103.05081/) (2021)
- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [On Architectures and Training for Raw Waveform Feature Extraction in ASR](https://mlsanity.com/paper/2104.04298/) (2021)
- [RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition](https://mlsanity.com/paper/2305.17782/) (2023)
- [Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project](https://mlsanity.com/paper/2309.15869/) (2023)
- [On Sampling-Based Training Criteria for Neural Language Modeling](https://mlsanity.com/paper/2104.10507/) (2021)
- [Self-Normalized Importance Sampling for Neural Language Modeling](https://mlsanity.com/paper/2111.06310/) (2021)
- [Analyzing And Improving Neural Speaker Embeddings for ASR](https://mlsanity.com/paper/2301.04571/) (2023)
- [Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR](https://mlsanity.com/paper/2403.10937/) (2024)

## Abstract (arXiv)

LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models. Incorporating them efficiently into decoding has been notoriously difficult. In this paper we present an approach based on a combination of one-pass decoding and lattice rescoring. We perform decoding with the LSTM-LM in the first pass but recombine hypothesis that share the last two words, afterwards we rescore the resulting lattice. We run our systems on GPGPU equipped machines and are able to produce competitive results on the Hub5'00 and Librispeech evaluation corpora with a runtime better than real-time. In addition we shortly investigate the possibility to carry out the full sum over all state-sequences belonging to a given word-hypothesis during decoding without recombination.