Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities

R. Haeb-Umbach, D. Geller, H. Ney, in: ICASSP, Minneapolis, 1993.

Conference Paper | English
Author
; ;
Abstract
Four methods were used to reduce the error rate of a continuous-density hidden Markov-model-based speech recognizer on the TI/NIST connected-digits recognition task. Energy thresholding sets a lower limit on the energy in each frequency channel to suppress spurious distortion accumulation caused by random noise. This led to an improvement in error rate by 15%. Spectrum normalization was used to compensate for across-speaker variations, resulting in an additional improvement by 20%. The acoustic resolution was increased up to 32 component densities per mixture. Each doubling of the number of component densities yielded a reduction in error rate by roughly 20%. Linear discriminant analysis was used for improved feature selection. A single class-independent transformation matrix was applied to a large input vector consisting of several adjacent frames, resulting in an improvement by 20% for high acoustic resolution. The final string error rate was 0.84%.
Publishing Year
Proceedings Title
ICASSP, Minneapolis
LibreCat-ID

Cite this

Haeb-Umbach R, Geller D, Ney H. Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities. In: ICASSP, Minneapolis. ; 1993.
Haeb-Umbach, R., Geller, D., & Ney, H. (1993). Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities. In ICASSP, Minneapolis.
@inproceedings{Haeb-Umbach_Geller_Ney_1993, title={Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities}, booktitle={ICASSP, Minneapolis}, author={Haeb-Umbach, Reinhold and Geller, Dieter and Ney, Hermann}, year={1993} }
Haeb-Umbach, Reinhold, Dieter Geller, and Hermann Ney. “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities.” In ICASSP, Minneapolis, 1993.
R. Haeb-Umbach, D. Geller, and H. Ney, “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities,” in ICASSP, Minneapolis, 1993.
Haeb-Umbach, Reinhold, et al. “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities.” ICASSP, Minneapolis, 1993.

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

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar