logo Idiap Research Institute        
 [BibTeX] [Marc21]
Robust triphone mapping for acoustic modeling
Type of publication: Conference paper
Citation: Cernak_INTERSPEECH_2012
Publication status: Accepted
Booktitle: Proceedings of Interspeech
Year: 2012
Month: September
Location: Portland, Oregon
Abstract: In this paper we revisit the recently proposed triphone mapping as an alternative to decision tree state clustering. We generalize triphone mapping to Kullback-Leibler based hidden Markov models for acoustic modeling and propose a modified training procedure for the Gaussian mixture model based acoustic modeling. We compare the triphone mapping to decision tree state clustering on the Wall Street journal task as well as in the context of an under-resourced language by using Greek data from the SpeechDat(II) corpus. Experiments reveal that triphone mapping has the best overall performance and is robust against varying the acoustic modeling technique as well as variable amounts of training data.
Keywords: acoustic modeling, Kullback-Leibler divergence, speech recognition, triphone mapping
Projects Idiap
Authors Cernak, Milos
Imseng, David
Bourlard, Hervé
Crossref by Cernak_Idiap-RR-02-2013
Added by: [UNK]
Total mark: 0
  • Cernak_INTERSPEECH_2012.pdf