000198446 001__ 198446
000198446 005__ 20190416055540.0
000198446 037__ $$aCONF
000198446 245__ $$aMultilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation
000198446 269__ $$a2014
000198446 260__ $$c2014
000198446 336__ $$aConference Papers
000198446 520__ $$aThis 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.
000198446 700__ $$aVu, Ngoc Thang
000198446 700__ $$0246030$$g160399$$aImseng, David
000198446 700__ $$aPovey, Daniel
000198446 700__ $$aMotlicek, Petr
000198446 700__ $$aSchultz, Tanja
000198446 700__ $$aBourlard, Hervé$$g117014$$0243348
000198446 7112_ $$cFlorence$$aProceedings IEEE International Conference on Acoustics, Speech and Signal Processing
000198446 8564_ $$uhttps://infoscience.epfl.ch/record/198446/files/Vu_ICASSP_2014.pdf$$zn/a$$s120885$$yn/a
000198446 909C0 $$xU10381$$0252189$$pLIDIAP
000198446 909CO $$ooai:infoscience.tind.io:198446$$qGLOBAL_SET$$pconf$$pSTI
000198446 937__ $$aEPFL-CONF-198446
000198446 970__ $$aVu_ICASSP_2014/LIDIAP
000198446 973__ $$aEPFL
000198446 980__ $$aCONF