logo Idiap Research Institute        
 [BibTeX] [Marc21]
Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation
Type of publication: Conference paper
Citation: Vu_ICASSP_2014
Publication status: Published
Booktitle: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2014
Month: May
Pages: 7639-7643
Publisher: IEEE
Location: Florence
ISSN: 1520-6149
DOI: 10.1109/ICASSP.2014.6855086
Abstract: This paper presents a study on multilingual deep neural network (DNN) based acoustic modeling and its application to new languages. We investigate the effect of phone merging on multilingual DNN in context of rapid language adaptation. Moreover, the combination of multilingual DNNs with Kullback--Leibler divergence based acoustic modeling (KL-HMM) is explored. Using ten different languages from the Globalphone database, our studies reveal that crosslingual acoustic model transfer through multilingual DNNs is superior to unsupervised RBM pre-training and greedy layer-wise supervised training. We also found that KL-HMM based decoding consistently outperforms conventional hybrid decoding, especially in low-resource scenarios. Furthermore, the experiments indicate that multilingual DNN training equally benefits from simple phoneset concatenation and manually derived universal phonesets.
Projects Idiap
Authors Vu, Ngoc Thang
Imseng, David
Povey, Daniel
Motlicek, Petr
Schultz, Tanja
Bourlard, Hervé
Added by: [UNK]
Total mark: 0
  • Vu_ICASSP_2014.pdf