Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR

V. Leutnant, R. Haeb-Umbach, in: 36. Deutsche Jahrestagung Fuer Akustik (DAGA 2010), 2010.

Conference Paper | English
Author
Abstract
Traditionally, ASR systems are based on hidden Markov models with Gaussian mixtures modelling the state-conditioned feature distribution. The inherent assumption of conditional independence, stating that a feature's likelihood solely depends on the current HMM state, makes the search computationally tractable, nevertheless has also been identified to be a major reason for the lack of robustness of such systems. Linear dynamic models have been proposed to overcome this weakness by employing a hidden dynamic state process underlying the observed features. Though performance of linear dynamic models on continuous speech/phone recognition tasks has been shown to be superior to that of equivalent static models, this approach still cannot compete with the established acoustic models. In this paper we consider the combination of hidden Markov models based on Gaussian mixture densities (GMM-HMMs) and linear dynamic models (LDMs) as the acoustic model for automatic speech recognition systems. In doing so, the individual strengths of both models, i.e. the modelling of long-term temporal dependencies by the GMM-HMM and the direct modelling of statistical dependencies between consecutive feature vectors by the LDM, are exploited. Phone classification experiments conducted on the TIMIT database indicate the prospective use of this approach for the application to continuous speech recognition.
Publishing Year
Proceedings Title
36. Deutsche Jahrestagung fuer Akustik (DAGA 2010)
LibreCat-ID

Cite this

Leutnant V, Haeb-Umbach R. Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR. In: 36. Deutsche Jahrestagung Fuer Akustik (DAGA 2010). ; 2010.
Leutnant, V., & Haeb-Umbach, R. (2010). Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR. In 36. Deutsche Jahrestagung fuer Akustik (DAGA 2010).
@inproceedings{Leutnant_Haeb-Umbach_2010, title={Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR}, booktitle={36. Deutsche Jahrestagung fuer Akustik (DAGA 2010)}, author={Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2010} }
Leutnant, Volker, and Reinhold Haeb-Umbach. “Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR.” In 36. Deutsche Jahrestagung Fuer Akustik (DAGA 2010), 2010.
V. Leutnant and R. Haeb-Umbach, “Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR,” in 36. Deutsche Jahrestagung fuer Akustik (DAGA 2010), 2010.
Leutnant, Volker, and Reinhold Haeb-Umbach. “Options for Modelling Temporal Statistical Dependencies in an Acoustic Model for ASR.” 36. Deutsche Jahrestagung Fuer Akustik (DAGA 2010), 2010.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar