TY  - JOUR
A1  - Dimitrakakis, Christos
A1  - Bengio, Samy
T1  - Phoneme and sentence-level ensembles for speech recognition
T2  - EURASIP Journal on Audio, Speech, and Music Processing
N2  - 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.
Y1  - 2011
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/3534
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30-94327
UR  - http://asmp.eurasipjournals.com/content/2011/1/426792
VL  - 2011
IS  - Nr. 1
ER  -