Investigation of Acoustic Modeling Techniques for LVCSR Systems

Xunying Liu, Mark J. F. Gales, Khe Chai Sim, Kai Yu

Abstract

The paper describes the use of several advanced acoustic modeling techniques for the 2004 CU-HTK large vocabulary speech recognition systems. These techniques include Gaussianization for speaker normalization, discriminative cluster adaptive training (CAT), subspace for precision and mean (SPAM) modeling of inverse covariances, and discriminative complexity control. Acoustic models featuring these techniques were integrated into a state-of-the-art 10 real-time multi-pass system with sophisticated adaptation for performance evaluation. Experimental results are presented on both broadcast news (BN) and conversational telephone speech (CTS) transcription tasks.
BibTeX
@inproceedings{liu2005investigation,
  author = {Xunying Liu and Mark J. F. Gales and Khe Chai Sim and Kai Yu},
  title = {{Investigation of Acoustic Modeling Techniques for LVCSR Systems}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2005},
  doi = {10.1109/icassp.2005.1415247},
}

Loading related content...

Figure