conference paper
Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities
Reinhold
Haeb-Umbach
author 242
Dieter
Geller
author
Hermann
Ney
author
54
department
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%.
1993
eng
ICASSP, Minneapolis
Haeb-Umbach, R., Geller, D., & Ney, H. (1993). Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities. In <i>ICASSP, Minneapolis</i>.
@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} }
R. Haeb-Umbach, D. Geller, H. Ney, in: ICASSP, Minneapolis, 1993.
Haeb-Umbach, Reinhold, et al. “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities.” <i>ICASSP, Minneapolis</i>, 1993.
Haeb-Umbach R, Geller D, Ney H. Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities. In: <i>ICASSP, Minneapolis</i>. ; 1993.
R. Haeb-Umbach, D. Geller, and H. Ney, “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities,” in <i>ICASSP, Minneapolis</i>, 1993.
Haeb-Umbach, Reinhold, Dieter Geller, and Hermann Ney. “Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities.” In <i>ICASSP, Minneapolis</i>, 1993.
117882019-07-12T05:28:16Z2019-07-12T08:49:38Z