A generative data augmentation model for enhancing Chinese dialect pronunciation prediction

NCUIR > College of Electrical Engineering & Computer Science > Department of Computer Science and information Engineering > journal & Dissertation > Item 987654321/106007

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/106007

Title:	A generative data augmentation model for enhancing Chinese dialect pronunciation prediction
Authors:	蔡宗翰;Lin, Chu-Cheng;Tsai, R. T-H
Contributors:	資訊電機學院資訊工程學系
Keywords:	Applied sciences;Chinese dialects;data augmentation;Data models;Dictionaries;Exact sciences and technology;generative model;Information, signal and communications theory;pronunciation database;Signal and communications theory;Signal processing;Signal representation. Spectral analysis;Signal, noise;Speech;Speech processing;Support vector machines;Telecommunications and information theory
Date:	2012-05-01
Issue Date:	2026-04-23 13:03:37 (UTC+8)
Publisher:	Institute of Electrical and Electronics Engineers Inc.;Piscataway, NJ: IEEE
Abstract:	摘要： Most spoken Chinese dialects lack comprehensive digital pronunciation databases, which are crucial for speech processing tasks. Given complete pronunciation databases for related dialects, one can use supervised learning techniques to predict a Chinese character's pronunciation in a target dialect based on the character's features and its pronunciation in other related dialects. Unfortunately, Chinese dialect pronunciation databases are far from complete. We propose a novel generative model that makes use of both existing dialect pronunciation data plus medieval rime books to discover patterns that exist in multiple dialects. The proposed model can augment missing dialectal pronunciations based on existing dialect pronunciation tables (even if incomplete) and the pronunciation data in rime books. The augmented pronunciation database can then be used in supervised learning settings. We evaluate the prediction accuracy in terms of phonological features, such as tone, initial phoneme, final phoneme, etc. For each character, features are evaluated on the whole, overall pronunciation feature accuracy (OPFA). Our first experimental results show that adding features from dialectal pronunciation data to our baseline rime-book model dramatically improves OPFA using the support vector machine (SVM) model. In the second experiment, we compare the performance of the SVM model using phonological features from closely related dialects with that of the model using phonological features from non-closely related dialects. The experimental results show that using features from closely related dialects results in higher accuracy. In the third experiment, we show that using our proposed data augmentation model to fill in missing data can increase the SVM model's OPFA by up to 7.6%. 其他題名： TASL 出版者： Piscataway, NJ: IEEE 出版日期： 2012-05-01 出處： IEEE transactions on audio, speech, and language processing, 2012-05, Vol.20 (4), p.1109-1117 資源來源： IEEE Electronic Library (IEL) 版權： 2015 INIST-CNRS 識別號： ISSN: 1558-7916 識別號： EISSN: 1558-7924 識別號： DOI: 10.1109/TASL.2011.2172424 識別號： CODEN: ITASD8
Appears in Collections:	[Department of Computer Science and information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	15	View/Open

社群 sharing

Loading...