A Bayesian view on acoustic model-based techniques for robust speech recognition
Maas R, Hümmer C, Sehr A, Kellermann W (2015)
Publication Language: English
Publication Status: Published
Publication Type: Journal article, Review article
Publication year: 2015
Journal
Book Volume: 2015
Pages Range: 1-16
Article Number: 103
Journal Issue: 1
DOI: 10.1186/s13634-015-0287-x
Abstract
This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition. The representatives of these classes can often be deduced from a Bayesian network that extends the conventional hidden Markov models used in speech recognition. These extensions, in turn, can in many cases be motivated from an underlying observation model that relates clean and distorted feature vectors. By identifying and converting the observation models into a Bayesian network representation, we formulate the corresponding compensation rules. We thus summarize the various approaches as approximations or modifications of the same Bayesian decoding rule leading to a unified view on known derivations as well as to new formulations for certain approaches.
Authors with CRIS profile
Roland Maas
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Christian Hümmer
Professur für Signalverarbeitung
Walter Kellermann
Professur für Signalverarbeitung
Involved external institutions
Germany (DE)How to cite
APA:
Maas, R., Hümmer, C., Sehr, A., & Kellermann, W. (2015). A Bayesian view on acoustic model-based techniques for robust speech recognition. EURASIP Journal on Advances in Signal Processing, 2015(1), 1-16. https://dx.doi.org/10.1186/s13634-015-0287-x
MLA:
Maas, Roland, et al. "A Bayesian view on acoustic model-based techniques for robust speech recognition." EURASIP Journal on Advances in Signal Processing 2015.1 (2015): 1-16.
BibTeX: Download