LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring

Neural network-based language models are commonly used in rescoring approaches to improve the quality of modern automatic speech recognition (ASR) systems. Most of the existing methods are computationally expensive since they use autoregressive language models. We propose a novel rescoring approach,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-04
Main Authors: Mitrofanov, Anton, Korenevskaya, Mariya, Podluzhny, Ivan, Khokhlov, Yuri, Laptev, Aleksandr, Andrusenko, Andrei, Ilin, Aleksei, Korenevsky, Maxim, Medennikov, Ivan, Romanenko, Aleksei
Format: Article
Language:English
Subjects:
Automatic speech recognition
Autoregressive models
Language
Lattices
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural network-based language models are commonly used in rescoring approaches to improve the quality of modern automatic speech recognition (ASR) systems. Most of the existing methods are computationally expensive since they use autoregressive language models. We propose a novel rescoring approach, which processes the entire lattice in a single call to the model. The key feature of our rescoring policy is a novel non-autoregressive Lattice Transformer Language Model (LT-LM). This model takes the whole lattice as an input and predicts a new language score for each arc. Additionally, we propose the artificial lattices generation approach to incorporate a large amount of text data in the LT-LM training process. Our single-shot rescoring performs orders of magnitude faster than other rescoring methods in our experiments. It is more than 300 times faster than pruned RNNLM lattice rescoring and N-best rescoring while slightly inferior in terms of WER.
ISSN:2331-8422