Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation
 
conference paper

Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation

Vu, Ngoc Thang
•
Imseng, David  
•
Povey, Daniel
Show more
2014
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing

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.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

Vu_ICASSP_2014.pdf

Access type

openaccess

Size

118.05 KB

Format

Adobe PDF

Checksum (MD5)

b216d82699fcf361ba4f1a6ab8b15bc2

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés