logo Idiap Research Institute        
 [BibTeX] [Marc21]
Hierarchical Processing of the Modulation Spectrum for GALE Mandarin LVCSR system
Type of publication: Conference paper
Citation: Valente_INTERSPEECH2009-2_2009
Booktitle: Proceedings of the 10thAnnual Conference of the International Speech Communication Association (Interspeech)
Year: 2009
Month: 9
Location: Brighton
Abstract: 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 approximatively 20% CER reduction on several data set.
Keywords: speech recognition., TANDEM features
Projects Idiap
Authors Valente, Fabio
Magimai.-Doss, Mathew
Plahl, Christian
Suman, Ravuri
Added by: [UNK]
Total mark: 0
  • Valente_INTERSPEECH2009-2_2009.pdf