CONF Vu_ICASSP_2014/IDIAP Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation Vu, Ngoc Thang Imseng, David Povey, Daniel Motlicek, Petr Schultz, Tanja Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/papers/2014/Vu_ICASSP_2014.pdf PUBLIC Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing Florence 2014 IEEE 7639-7643 1520-6149 10.1109/ICASSP.2014.6855086 doi 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.