Saved in:
Bibliographic Details
Main Authors: Lu, Junyu, Jiang, Di, Hong, Mengze, Wei, Victor Junqiu, Guo, Qintian, Su, Zhiyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.04393
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908519171620864
author Lu, Junyu
Jiang, Di
Hong, Mengze
Wei, Victor Junqiu
Guo, Qintian
Su, Zhiyang
author_facet Lu, Junyu
Jiang, Di
Hong, Mengze
Wei, Victor Junqiu
Guo, Qintian
Su, Zhiyang
contents Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR) systems, this paper introduces a novel method named Contextualized Token Discrimination (CTD) to conduct effective speech query correction. In CTD, we first employ BERT to generate token-level contextualized representations and then construct a composition layer to enhance semantic information. Finally, we produce the correct query according to the aggregated token representation, correcting the incorrect tokens by comparing the original token representations and the contextualized representations. Extensive experiments demonstrate the superior performance of our proposed method across all metrics, and we further present a new benchmark dataset with erroneous ASR transcriptions to offer comprehensive evaluations for audio query correction.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04393
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contextualized Token Discrimination for Speech Search Query Correction
Lu, Junyu
Jiang, Di
Hong, Mengze
Wei, Victor Junqiu
Guo, Qintian
Su, Zhiyang
Sound
Computation and Language
Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR) systems, this paper introduces a novel method named Contextualized Token Discrimination (CTD) to conduct effective speech query correction. In CTD, we first employ BERT to generate token-level contextualized representations and then construct a composition layer to enhance semantic information. Finally, we produce the correct query according to the aggregated token representation, correcting the incorrect tokens by comparing the original token representations and the contextualized representations. Extensive experiments demonstrate the superior performance of our proposed method across all metrics, and we further present a new benchmark dataset with erroneous ASR transcriptions to offer comprehensive evaluations for audio query correction.
title Contextualized Token Discrimination for Speech Search Query Correction
topic Sound
Computation and Language
url https://arxiv.org/abs/2509.04393