The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Walaupun penyelidikan pengecaman pertuturan berasaskan hujung ke hujung untuk penukaran kod Mandarin-Inggeris telah menarik minat yang semakin meningkat, ia tetap mencabar kerana kekurangan data. Pendekatan meta-pembelajaran popular dengan pemodelan sumber rendah menggunakan data sumber tinggi, tetapi ia tidak menggunakan sepenuhnya data penukaran kod sumber rendah. Oleh itu, kami mencadangkan rangka kerja latihan pengesahan silang dua kali ganda digabungkan dengan pendekatan meta-pembelajaran. Eksperimen pada korpus SEAME menunjukkan kesan kaedah kami.
Zheying HUANG
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Ji XU
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Qingwei ZHAO
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Pengyuan ZHANG
Chinese Academy of Sciences,University of Chinese Academy of Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Zheying HUANG, Ji XU, Qingwei ZHAO, Pengyuan ZHANG, "A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 9, pp. 1639-1642, September 2022, doi: 10.1587/transinf.2022EDL8036.
Abstract: Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8036/_p
Salinan
@ARTICLE{e105-d_9_1639,
author={Zheying HUANG, Ji XU, Qingwei ZHAO, Pengyuan ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition},
year={2022},
volume={E105-D},
number={9},
pages={1639-1642},
abstract={Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.},
keywords={},
doi={10.1587/transinf.2022EDL8036},
ISSN={1745-1361},
month={September},}
Salinan
TY - JOUR
TI - A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1639
EP - 1642
AU - Zheying HUANG
AU - Ji XU
AU - Qingwei ZHAO
AU - Pengyuan ZHANG
PY - 2022
DO - 10.1587/transinf.2022EDL8036
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2022
AB - Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.
ER -