On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition

V. Leutnant, R. Haeb-Umbach, in: Interspeech 2010, 2010.

Conference Paper | English
Author
Abstract
Linear dynamic models (LDMs) have been shown to be a viable alternative to hidden Markov models (HMMs) on small-vocabulary recognition tasks, such as phone classification. In this paper we investigate various statistical model combination approaches for a hybrid HMM-LDM recognizer, resulting in a phone classification performance that outperforms the best individual classifier. Further, we report on continuous speech recognition experiments on the AURORA4 corpus, where the model combination is carried out on wordgraph rescoring. While the hybrid system improves the HMM system in the case of monophone HMMs, the performance of the triphone HMM model could not be improved by monophone LDMs, asking for the need to introduce context-dependency also in the LDM model inventory.
Publishing Year
Proceedings Title
Interspeech 2010
LibreCat-ID

Cite this

Leutnant V, Haeb-Umbach R. On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition. In: Interspeech 2010. ; 2010.
Leutnant, V., & Haeb-Umbach, R. (2010). On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition. In Interspeech 2010.
@inproceedings{Leutnant_Haeb-Umbach_2010, title={On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition}, booktitle={Interspeech 2010}, author={Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2010} }
Leutnant, Volker, and Reinhold Haeb-Umbach. “On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition.” In Interspeech 2010, 2010.
V. Leutnant and R. Haeb-Umbach, “On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition,” in Interspeech 2010, 2010.
Leutnant, Volker, and Reinhold Haeb-Umbach. “On the Exploitation of Hidden Markov Models and Linear Dynamic Models in a Hybrid Decoder Architecture for Continuous Speech Recognition.” Interspeech 2010, 2010.

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

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar