Papers
arxiv:2309.15223

Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition

Published on Sep 26, 2023
· Submitted by akhaliq on Sep 28, 2023
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high computational cost of scaling up the pretraining stage and adapting the pretrained models to specific domains limit their practical use in rescoring. Here we present a method based on low-rank decomposition to train a rescoring BERT model and adapt it to new domains using only a fraction (0.08%) of the pretrained parameters. These inserted matrices are optimized through a discriminative training objective along with a correlation-based regularization loss. The proposed low-rank adaptation Rescore-BERT (LoRB) architecture is evaluated on LibriSpeech and internal datasets with decreased training times by factors between 5.4 and 3.6.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2309.15223 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2309.15223 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2309.15223 in a Space README.md to link it from this page.

Collections including this paper 5