Deep CLAS: Deep Contextual Listen, Attend and Spell

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Mengzhi, Xiong, Shifu, Wan, Genshun, Chen, Hang, Gao, Jianqing, Dai, Lirong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916532101054464
author Wang, Mengzhi
Xiong, Shifu
Wan, Genshun
Chen, Hang
Gao, Jianqing
Dai, Lirong
author_facet Wang, Mengzhi
Xiong, Shifu
Wan, Genshun
Chen, Hang
Gao, Jianqing
Dai, Lirong
contents Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which lead to insufficient use of contextual information. In this work, we propose deep CLAS to use contextual information better. We introduce bias loss forcing model to focus on contextual information. The query of bias attention is also enriched to improve the accuracy of the bias attention score. To get fine-grained contextual information, we replace phrase-level encoding with character-level encoding and encode contextual information with conformer rather than LSTM. Moreover, we directly use the bias attention score to correct the output probability distribution of the model. Experiments using the public AISHELL-1 and AISHELL-NER. On AISHELL-1, compared to CLAS baselines, deep CLAS obtains a 65.78% relative recall and a 53.49% relative F1-score increase in the named entity recognition scene.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17603
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep CLAS: Deep Contextual Listen, Attend and Spell
Wang, Mengzhi
Xiong, Shifu
Wan, Genshun
Chen, Hang
Gao, Jianqing
Dai, Lirong
Computation and Language
Sound
Audio and Speech Processing
Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which lead to insufficient use of contextual information. In this work, we propose deep CLAS to use contextual information better. We introduce bias loss forcing model to focus on contextual information. The query of bias attention is also enriched to improve the accuracy of the bias attention score. To get fine-grained contextual information, we replace phrase-level encoding with character-level encoding and encode contextual information with conformer rather than LSTM. Moreover, we directly use the bias attention score to correct the output probability distribution of the model. Experiments using the public AISHELL-1 and AISHELL-NER. On AISHELL-1, compared to CLAS baselines, deep CLAS obtains a 65.78% relative recall and a 53.49% relative F1-score increase in the named entity recognition scene.
title Deep CLAS: Deep Contextual Listen, Attend and Spell
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.17603