Investigations into Uncertainty Decoding Employing a Discrete Feature Space for Noise Robust Automatic Speech Recognition

Conference: Sprachkommunikation 2008 - 8. ITG-Fachtagung
10/08/2008 - 10/10/2008 at Aachen, Germany

Proceedings: Sprachkommunikation 2008

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Ion, Valentin; Häb-Umbach, Reinhold (University of Paderborn, Dept. of Communications Engineering, 33098 Paderborn)

Abstract:
This paper addresses the robustness of automatic speech recognition to environmental noise. In order to account for reliability of the clean feature estimate we employ the feature posterior density conditioned on observed noisy features to perform uncertainty decoding. We investigate two approaches to estimate the posterior using a discrete feature space, first conditioning only on the current observation, and second on the whole feature sequence of an utterance. Experiments with Aurora 2 showed that the latter provides slightly better performance, as it allows for exploiting the temporal correlations between consecutive features.