Next Article in Journal
Group Decision Making Based on Triangular Neutrosophic Cubic Fuzzy Einstein Hybrid Weighted Averaging Operators
Next Article in Special Issue
EasyStego: Robust Steganography Based on Quick-Response Barcodes for Crossing Domains
Previous Article in Journal
The kS3-Module Algebra Structures on M3(k)
Previous Article in Special Issue
Detecting Word-Based Algorithmically Generated Domains Using Semantic Analysis
Article Menu
Issue 2 (February) cover image

Export Article

Open AccessArticle
Symmetry 2019, 11(2), 179; https://doi.org/10.3390/sym11020179

Cross-Language End-to-End Speech Recognition Research Based on Transfer Learning for the Low-Resource Tujia Language

1
College of Computer & Information Engineering, Beijing Technology and Business University, Beijing 100048, China
2
Institute of Ethnology & Anthropology, Chinese Academy of Social Sciences, Beijing 100081, China
*
Author to whom correspondence should be addressed.
Received: 17 December 2018 / Revised: 27 January 2019 / Accepted: 29 January 2019 / Published: 2 February 2019
(This article belongs to the Special Issue Information Technology and Its Applications 2018)
Full-Text   |   PDF [2647 KB, uploaded 2 February 2019]   |  

Abstract

To rescue and preserve an endangered language, this paper studied an end-to-end speech recognition model based on sample transfer learning for the low-resource Tujia language. From the perspective of the Tujia language international phonetic alphabet (IPA) label layer, using Chinese corpus as an extension of the Tujia language can effectively solve the problem of an insufficient corpus in the Tujia language, constructing a cross-language corpus and an IPA dictionary that is unified between the Chinese and Tujia languages. The convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) network were used to extract the cross-language acoustic features and train shared hidden layer weights for the Tujia language and Chinese phonetic corpus. In addition, the automatic speech recognition function of the Tujia language was realized using the end-to-end method that consists of symmetric encoding and decoding. Furthermore, transfer learning was used to establish the model of the cross-language end-to-end Tujia language recognition system. The experimental results showed that the recognition error rate of the proposed model is 46.19%, which is 2.11% lower than the that of the model that only used the Tujia language data for training. Therefore, this approach is feasible and effective. View Full-Text
Keywords: low-resource speech recognition; Tujia language; cross-language end-to-end; transfer learning low-resource speech recognition; Tujia language; cross-language end-to-end; transfer learning
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Yu, C.; Chen, Y.; Li, Y.; Kang, M.; Xu, S.; Liu, X. Cross-Language End-to-End Speech Recognition Research Based on Transfer Learning for the Low-Resource Tujia Language. Symmetry 2019, 11, 179.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Symmetry EISSN 2073-8994 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top