Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data

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 o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Meng, Helen, Lianhong Cai
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
bidirectional long short-term memory (BLSTM)
cross-lingual
emphasis detection
Feature extraction
multilingual
Recurrent neural networks
Speech
Speech recognition
Support vector machines
Training data
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2379-190X
DOI:10.1109/ICASSP.2017.7953231