ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Hierarchical processing of the modulation spectrum for GALE Mandarin LVCSR system

Fabio Valente, Mathew Magimai-Doss, C. Plahl, Suman Ravuri

This paper aims at investigating the use of TANDEM features based on hierarchical processing of the modulation spectrum. The study is done in the framework of the GALE project for recognition of Mandarin Broadcast data. We describe the improvements obtained using the hierarchical processing and the addition of features like pitch and short-term critical band energy. Results are consistent with previous findings on a different LVCSR task suggesting that the proposed technique is effective and robust across several conditions. Furthermore we describe integration into RWTH GALE LVCSR system trained on 1600 hours of Mandarin data and present progress across the GALE 2007 and GALE 2008 RWTH systems resulting in approximately 20% CER reduction on several data set.


doi: 10.21437/Interspeech.2009-750

Cite as: Valente, F., Magimai-Doss, M., Plahl, C., Ravuri, S. (2009) Hierarchical processing of the modulation spectrum for GALE Mandarin LVCSR system. Proc. Interspeech 2009, 2963-2966, doi: 10.21437/Interspeech.2009-750

@inproceedings{valente09_interspeech,
  author={Fabio Valente and Mathew Magimai-Doss and C. Plahl and Suman Ravuri},
  title={{Hierarchical processing of the modulation spectrum for GALE Mandarin LVCSR system}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={2963--2966},
  doi={10.21437/Interspeech.2009-750}
}