logo Idiap Research Institute        
 [BibTeX] [Marc21]
Posterior Features for Template-based ASR
Type of publication: Conference paper
Citation: Soldo_ICASSP_2011
Booktitle: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing
Year: 2011
Month: May
Location: Prague, Czech Republic
Abstract: This paper investigates the use of phoneme class conditional probabilities as features (posterior features) for template-based ASR. Using 75 words and 600 words task-independent and speaker-independent setup on Phonebook database, we investigate the use of different posterior distribution estimators, different distance measures that are better suited for posterior distributions, and different training data. The reported experiments clearly demonstrate that posterior features are always superior, and generalize better than other classical acoustic features (at the cost of training a posterior distribution estimator).
Keywords: Posterior features, speech recognition, template-based approach
Projects Idiap
Authors Soldo, Serena
Magimai.-Doss, Mathew
Pinto, Joel Praveen
Bourlard, Hervé
Added by: [UNK]
Total mark: 0
  • Soldo_ICASSP_2011.pdf