# An Empirical Study of Language Model Integration for Transducer based Speech Recognition

arXiv: https://arxiv.org/abs/2203.16776 · HTML: https://mlsanity.com/paper/2203.16776/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [Coordinate Descent Algorithms](https://mlsanity.com/paper/1502.04759/) (2015)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [An analysis of incorporating an external language model into a sequence-to-sequence model](https://mlsanity.com/paper/1712.01996/) (2017)
- [Hybrid Autoregressive Transducer (hat)](https://mlsanity.com/paper/2003.07705/) (2020)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2011.01991/) (2020)
- [A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2002.11268/) (2020)
- [On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition](https://mlsanity.com/paper/2005.14327/) (2020)
- [Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability](https://mlsanity.com/paper/2007.15188/) (2020)
- [Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2102.01380/) (2021)
- [Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models](https://mlsanity.com/paper/2104.05544/) (2021)
- [Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition](https://mlsanity.com/paper/2106.02302/) (2021)
- [On Language Model Integration for RNN Transducer based Speech Recognition](https://mlsanity.com/paper/2110.06841/) (2021)

## Built on by (most cited first, 2 of 2)

- [Blank-regularized CTC for Frame Skipping in Neural Transducer](https://mlsanity.com/paper/2305.11558/) (2023)
- [On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers](https://mlsanity.com/paper/2309.14130/) (2023)

## Abstract (arXiv)

Utilizing text-only data with an external language model (ELM) in end-to-end RNN-Transducer (RNN-T) for speech recognition is challenging. Recently, a class of methods such as density ratio (DR) and internal language model estimation (ILME) have been developed, outperforming the classic shallow fusion (SF) method. The basic idea behind these methods is that RNN-T posterior should first subtract the implicitly learned internal language model (ILM) prior, in order to integrate the ELM. While recent studies suggest that RNN-T only learns some low-order language model information, the DR method uses a well-trained neural language model with full context, which may be inappropriate for the estimation of ILM and deteriorate the integration performance. Based on the DR method, we propose a low-order density ratio method (LODR) by replacing the estimation with a low-order weak language model. Extensive empirical experiments are conducted on both in-domain and cross-domain scenarios on English LibriSpeech & Tedlium-2 and Chinese WenetSpeech & AISHELL-1 datasets. It is shown that LODR consistently outperforms SF in all tasks, while performing generally close to ILME and better than DR in most tests.