Phoneme and sentence-level ensembles for speech recognition
Journal article, 2011

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. © 2011 Christos Dimitrakakis and Samy Bengio.


Christos Dimitrakakis

Chalmers, Computer Science and Engineering (Chalmers), Computing Science (Chalmers)

S. Bengio

Eurasip Journal on Audio, Speech, and Music Processing

1687-4714 (ISSN) 1687-4722 (eISSN)

Vol. 2011

Areas of Advance

Information and Communication Technology

Subject Categories

Computer and Information Science



More information