logo Idiap Research Institute        
 [BibTeX] [Marc21]
Robust triphone mapping for acoustic modeling
Type of publication: Idiap-RR
Citation: Cernak_Idiap-RR-02-2013
Number: Idiap-RR-02-2013
Year: 2013
Month: 1
Institution: Idiap
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.
Crossref: Cernak_INTERSPEECH_2012:
Robust triphone mapping for acoustic modeling, Cernak, Milos, Imseng, David and Bourlard, Hervé, in: Proceedings of Interspeech, Portland, Oregon, 2012
Projects Idiap
Authors Cernak, Milos
Imseng, David
Bourlard, Hervé
Added by: [ADM]
Total mark: 0
  • Cernak_Idiap-RR-02-2013.pdf (MD5: 639f0d98f239cffe0ec977056e37c73f)