Saved in:
Bibliographic Details
Main Authors: Cheng, Gaofeng, Lu, Haitian, Yang, Chengxu, Wang, Xuyang, Li, Ta, Yan, Yonghong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.00804
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929654355460096
author Cheng, Gaofeng
Lu, Haitian
Yang, Chengxu
Wang, Xuyang
Li, Ta
Yan, Yonghong
author_facet Cheng, Gaofeng
Lu, Haitian
Yang, Chengxu
Wang, Xuyang
Li, Ta
Yan, Yonghong
contents Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation lexicons. In this paper, we propose a data-driven method to automatically acquire these pronunciation correlations, called automatic text pronunciation correlation (ATPC). The supervision required for this method is consistent with the supervision needed for training end-to-end automatic speech recognition (E2E-ASR) systems, i.e., speech and corresponding text annotations. First, the iteratively-trained timestamp estimator (ITSE) algorithm is employed to align the speech with their corresponding annotated text symbols. Then, a speech encoder is used to convert the speech into speech embeddings. Finally, we compare the speech embeddings distances of different text symbols to obtain ATPC. Experimental results on Mandarin show that ATPC enhances E2E-ASR performance in contextual biasing and holds promise for dialects or languages lacking artificial pronunciation lexicons.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00804
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing
Cheng, Gaofeng
Lu, Haitian
Yang, Chengxu
Wang, Xuyang
Li, Ta
Yan, Yonghong
Audio and Speech Processing
Computation and Language
Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation lexicons. In this paper, we propose a data-driven method to automatically acquire these pronunciation correlations, called automatic text pronunciation correlation (ATPC). The supervision required for this method is consistent with the supervision needed for training end-to-end automatic speech recognition (E2E-ASR) systems, i.e., speech and corresponding text annotations. First, the iteratively-trained timestamp estimator (ITSE) algorithm is employed to align the speech with their corresponding annotated text symbols. Then, a speech encoder is used to convert the speech into speech embeddings. Finally, we compare the speech embeddings distances of different text symbols to obtain ATPC. Experimental results on Mandarin show that ATPC enhances E2E-ASR performance in contextual biasing and holds promise for dialects or languages lacking artificial pronunciation lexicons.
title Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing
topic Audio and Speech Processing
Computation and Language
url https://arxiv.org/abs/2501.00804