Phoneme and sentence-level ensembles for speech recognition

We address the question of whether and how boosting and bagging can be used for speech recognition. In order to do this, we compare two different boosting schemes, one at the phoneme level and one at the utterance level,
We address the question of whether and how boosting and bagging can be used for speech recognition. In order to do this, we compare two different boosting schemes, one at the phoneme level and one at the utterance level, with a phoneme-level bagging scheme. We control for many parameters and other choices, such as the state inference scheme used. In an unbiased experiment, we clearly show that the gain of boosting methods compared to a single hidden Markov model is in all cases only marginal, while bagging significantly outperforms all other methods. We thus conclude that bagging methods, which have so far been overlooked in favour of boosting, should be examined more closely as a potentially useful ensemble learning technique for speech recognition.
show moreshow less

Download full text files

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

    Share in Twitter Search Google Scholar
Metadaten
Author:Christos Dimitrakakis, Samy Bengio
URN:urn:nbn:de:hebis:30-94327
URL:http://asmp.eurasipjournals.com/content/2011/1/426792
DOI:http://dx.doi.org/doi:10.1155/2011/426792
Parent Title (German):EURASIP Journal on Audio, Speech, and Music Processing
Document Type:Article
Language:English
Date of Publication (online):2011/04/14
Year of first Publication:2011
Publishing Institution:Univ.-Bibliothek Frankfurt am Main
Release Date:2011/04/14
Volume:2011
HeBIS PPN:304198838
Institutes:Frankfurt Institute for Advanced Studies (FIAS)
Dewey Decimal Classification:610 Medizin und Gesundheit
Sammlungen:Universitätspublikationen
Licence (German):License Logo Veröffentlichungsvertrag für Publikationen

$Rev: 11761 $