Saved in:
Bibliographic Details
Main Authors: Wang, Peng, Yang, Yifan, Liang, Zheng, Tan, Tian, Zhang, Shiliang, Chen, Xie
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.07648
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914829735821312
author Wang, Peng
Yang, Yifan
Liang, Zheng
Tan, Tian
Zhang, Shiliang
Chen, Xie
author_facet Wang, Peng
Yang, Yifan
Liang, Zheng
Tan, Tian
Zhang, Shiliang
Chen, Xie
contents Despite advancements of end-to-end (E2E) models in speech recognition, named entity recognition (NER) is still challenging but critical for semantic understanding. Previous studies mainly focus on various rule-based or attention-based contextual biasing algorithms. However, their performance might be sensitive to the biasing weight or degraded by excessive attention to the named entity list, along with a risk of false triggering. Inspired by the success of the class-based language model (LM) in NER in conventional hybrid systems and the effective decoupling of acoustic and linguistic information in the factorized neural Transducer (FNT), we propose C-FNT, a novel E2E model that incorporates class-based LMs into FNT. In C-FNT, the LM score of named entities can be associated with the name class instead of its surface form. The experimental results show that our proposed C-FNT significantly reduces error in named entities without hurting performance in general word recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07648
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer
Wang, Peng
Yang, Yifan
Liang, Zheng
Tan, Tian
Zhang, Shiliang
Chen, Xie
Audio and Speech Processing
Computation and Language
Sound
Despite advancements of end-to-end (E2E) models in speech recognition, named entity recognition (NER) is still challenging but critical for semantic understanding. Previous studies mainly focus on various rule-based or attention-based contextual biasing algorithms. However, their performance might be sensitive to the biasing weight or degraded by excessive attention to the named entity list, along with a risk of false triggering. Inspired by the success of the class-based language model (LM) in NER in conventional hybrid systems and the effective decoupling of acoustic and linguistic information in the factorized neural Transducer (FNT), we propose C-FNT, a novel E2E model that incorporates class-based LMs into FNT. In C-FNT, the LM score of named entities can be associated with the name class instead of its surface form. The experimental results show that our proposed C-FNT significantly reduces error in named entities without hurting performance in general word recognition.
title Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2309.07648