@inproceedings{8e27d96ace6b4cf4a3dcae518baa8d5d,
title = "Comparison of Two Cross-lingual AF Extraction Methods",
abstract = "In this paper we propose two different cross-lingual articulatory features (AFs) extraction methods and build recognition systems based on cross-lingual AFs. The AF extractors are trained from source language (English) and cross-lingual AFs are generated for the target language (Mandarin) using the trained extractors. Experiments are carried with two kinds of AFs extraction architectures, mutilayer perception (MLP) and the Bidirectional Long Short-Term Memory (BLSTM) based connectionist temporal classification (CTC). The MLP architectures requires frame-level AF label which converted by phone alignment obtained from GMM-HMM using Phone-to-AF mapping, while the BLSTM-based CTC eliminates the need for alignments. The Mandarin speech recognition system is built by the joint features which are concatenated with AFs and MFCC. The results show that the using of cross-lingual AFs can improve the performance of ASR task on THCHS-30. Among two architectures, cross-lingual AFs extracted using BLSTM-based CTC gives better recognition performance.",
keywords = "Articulatory feature, Connectionist temporal classification, Cross-lingual, Speech recognition",
author = "Shixuan Du and Qingran Zhan and Yahui Shan and Xiang Xie",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2nd IEEE International Conference on Information Communication and Signal Processing, ICICSP 2019 ; Conference date: 28-09-2019 Through 30-09-2019",
year = "2019",
month = sep,
doi = "10.1109/ICICSP48821.2019.8958606",
language = "English",
series = "2019 2nd IEEE International Conference on Information Communication and Signal Processing, ICICSP 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "262--266",
booktitle = "2019 2nd IEEE International Conference on Information Communication and Signal Processing, ICICSP 2019",
address = "United States",
}