logo Idiap Research Institute        
 [BibTeX] [Marc21]
Posterior Features Applied to Speech Recognition Tasks with Limited Training Data
Type of publication: Idiap-RR
Citation: aradilla:rr08-15
Number: Idiap-RR-15-2008
Year: 2008
Institution: IDIAP
Abstract: This paper describes an approach where posterior-based features are applied in those recognition tasks where the amount of training data is insufficient to obtain a reliable estimate of the speech variability. A template matching approach is considered in this paper where posterior features are obtained from a MLP trained on an auxiliary database. Thus, the speech variability present in the features is reduced by applying the speech knowledge captured on the auxiliary database. When compared to state-of-the-art systems, this approach outperforms acoustic-based techniques and obtains comparable results to grapheme-based approaches. Moreover, the proposed method can be directly combined with other posterior-based HMM systems. This combination successfully exploits the complementarity between templates and parametric models.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors Aradilla, Guillermo
Bourlard, Hervé
Magimai.-Doss, Mathew
Added by: [UNK]
Total mark: 0
Attachments
  • aradilla-idiap-rr-08-15.pdf
  • aradilla-idiap-rr-08-15.ps.gz
Notes