Academic Journals Database
Disseminating quality controlled scientific knowledge

Phoneme and Sentence-Level Ensembles for Speech Recognition

ADD TO MY LIST
 
Author(s): Dimitrakakis Christos | Bengio Samy

Journal: EURASIP Journal on Audio, Speech, and Music Processing
ISSN 1687-4714

Volume: 2011;
Issue: 1;
Start page: 426792;
Date: 2011;
Original page

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.
RPA Switzerland

Robotic Process Automation Switzerland

    

Tango Jona
Tangokurs Rapperswil-Jona