@inproceedings{334a483ae5b240169a30e0ea5aa0f632,
title = "Multilingual bottle-neck feature learning from untranscribed speech",
abstract = "We propose to learn a low-dimensional feature representation for multiple languages without access to their manual transcription. The multilingual features are extracted from a shared bottleneck layer of a multi-task learning deep neural network which is trained using un-supervised phoneme-like labels. The unsupervised phoneme-like labels are obtained from language-dependent Dirichlet process Gaussian mixture models (DPGMMs). Vocal tract length normalization (VTLN) is applied to mel-frequency cepstral coefficients to reduce talker variation when DPGMMs are trained. The proposed features are evaluated using the ABX phoneme discriminability test in the Zero Resource Speech Challenge 2017. In the experiments, we show that the proposed features perform well across different languages, and they consistently outperform our previously proposed DPGMM posteriorgrams which topped the performance in the same challenge in 2015.",
keywords = "low/zero-resource, Multi-task learning, multilingual feature, unsupervised feature learning",
author = "Hongjie Chen and Leung, {Cheung Chi} and Lei Xie and Bin Ma and Haizhou Li",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 ; Conference date: 16-12-2017 Through 20-12-2017",
year = "2017",
month = jul,
day = "2",
doi = "10.1109/ASRU.2017.8269009",
language = "英语",
series = "2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "727--733",
booktitle = "2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings",
}