Dynamic Bayesian Networks for Automatic Speech Recognition
Abstract
State-of-the-art automatic speech recognition (ASR) systems are based on probabilistic modelling of the speech signal using Hidden Markov Models. The limitations of these systems under real life conditions arose a question about the robustness of the underlying acoustic modelling methodology. The scope of my thesis is to explore the formalism of Probabilistic Graphical Models, particularly Dynamic Bayesian Networks, from a theoretical and practical point of view, with the aim of developing reliable models of speech and of developing robust ASR systems.
Cite
Text
Deviren. "Dynamic Bayesian Networks for Automatic Speech Recognition." AAAI Conference on Artificial Intelligence, 2002. doi:10.5555/777092.777254Markdown
[Deviren. "Dynamic Bayesian Networks for Automatic Speech Recognition." AAAI Conference on Artificial Intelligence, 2002.](https://mlanthology.org/aaai/2002/deviren2002aaai-dynamic/) doi:10.5555/777092.777254BibTeX
@inproceedings{deviren2002aaai-dynamic,
title = {{Dynamic Bayesian Networks for Automatic Speech Recognition}},
author = {Deviren, Murat},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2002},
pages = {981},
doi = {10.5555/777092.777254},
url = {https://mlanthology.org/aaai/2002/deviren2002aaai-dynamic/}
}