Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer

Citations Over TimeTop 10% of 2021 papers

Abstract

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has proposed various fusion methods to incorporate external NNLMs into end-to-end ASR to address this weakness. In this paper, we propose extensions to these techniques that allow RNN-T to exploit external NNLMs during both training and inference time, resulting in 13-18% relative Word Error Rate improvement on Librispeech compared to strong baselines. Furthermore, our methods do not incur extra algorithmic latency and allow for flexible plug- and-play of different NNLMs without re-training. We also share in-depth analysis to better understand the benefits of the different NNLM fusion methods. Our work provides a reliable technique for leveraging unpaired text data to significantly improve RNN-T while keeping the system streamable, flexible, and lightweight.

Related Papers

• → Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks(2016)146 cited
• → Bidirectional recurrent neural network language models for automatic speech recognition(2015)83 cited
• → Language Models with RNNs for Rescoring Hypotheses of Russian ASR(2016)3 cited
• → Deep Learning Based Language Modeling for Domain-Specific Speech Recognition(2017)1 cited
• → Large Scale Language Modeling in Automatic Speech Recognition(2012)37 cited