We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to lattice re-scoring that allows for longer range history captured by a transfomer-based language model and takes advantage of a transformer's ability to avoid computing sequentially.
@article{arxiv.2001.01140,
title = {Transformer-based language modeling and decoding for conversational speech recognition},
author = {Kareem Nassar},
journal= {arXiv preprint arXiv:2001.01140},
year = {2020}
}