@InProceedings{Beschorner2012_141,
author = {Andreas Beschorner and Dietrich Klakow},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2012.},
title = {Continuous speech recognition using Correlation features and structured SVM probability output},
year = {2012},
editor = {Matthias Wolff},
month = mar,
pages = {65--72},
publisher = {TUDpress, Dresden},
abstract = {One potential area for improvement in continuous speech recognition is
the modelling of phoneme transitions (not transition probabilties) arising from the
non-stationarity of speech: refined models can then be used to compute probability
distributions which can serve as emission probabilities for HMM-based speech
recognition systems. In this paper we present our approach to improving phoneme
transition modelling. Building on our previous work, we employ a phoneme partition
approach (SME: start, middle, and end states) to build a structure of support
vector (SV) classifiers as our main discriminative method. For the phoneme classification step, cross correlation features based on MFCC-vectors are computed
and classified within the SME structure. Additionally, we make use of a special
reproducing kernel build upon the correlation features, thus offering a direct
integration into the SV classifiers. This paper discusses the computation of the
afore-mentioned probability outputs as well as initial results using these outputs as
emission probabilities in HMMs representing phonemes, applied within a standard
speech recognition system.},
isbn = {978-3-942710-81-7},
issn = {0940-6832},
keywords = {Spracherkennung},
url = {https://www.essv.de/pdf/2012_65_72.pdf},
}