Phoneme and Sentence-Level Ensembles for Speech Recognition. (7th February 2011)

• Record Type: Journal Article
• Authors: Dimitrakakis Dimitrakakis, Christos Christos; Bengio Bengio, Samy Samy
• Other Names: Nöth Nöth Elmar Elmar Academic Editor.
• Is Part Of: EURASIP journal on audio, speech, and music processing. Volume 2011(2011)
• Publication Date: 2011-02-07
• Subjects: Sound -- Recording and reproducing -- Digital techniques -- Periodicals; Computer sound processing -- Periodicals; Computer sound processing; Sound -- Recording and reproducing -- Digital techniques; Periodicals; Electronic journal; Electronic journals; 620.2
• DOI: 10.1155/2011/426792
• Languages: English
• ISSNs: 1687-4714

Abstract

Abstract : 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.