Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data
Lists
Only you see this
Abstract
Bidirectional long short-term memory (BLSTM) recurrent neural network (RNN) has achieved state-of-the-art performance in many sequence processing problems given its capability in capturing contextual information. However, for languages with limited amount of training data, it is still difficult to obtain a high quality BLSTM model for emphasis detection, the aim of which is to recognize the emphasized speech segments from natural speech. To address this problem, in this paper, we propose a multilingual BLSTM (MTL-BLSTM) model where the hidden layers are shared across different languages while the softmax output layer is language-dependent. The MTL-BLSTM can learn cross-lingual knowledge and transfer this knowledge to both languages to improve the emphasis detection performance. Experimental results demonstrate our method can outperform the comparison methods over 2-15.6% and 2.9-15.4% on the English corpus and Mandarin corpus in terms of relative F1-measure, respectively.
BibTeX
@inproceedings{ning2017learning,
author = {Yishuang Ning and Zhiyong Wu and Runnan Li and Jia Jia and Mingxing Xu and Helen M. Meng and Lianhong Cai},
title = {{Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2017},
doi = {10.1109/icassp.2017.7953231},
}Loading related content...