The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1993)
Minneapolis, MN, USA
Apr. 27, 1993 to Apr. 30, 1993
ISBN: 0-7803-0946-4
pp: 239-242
R. Haeb-Umbach , Philips GmbH Res. Lab., Aachen, Germany
D. Geller , Philips GmbH Res. Lab., Aachen, Germany
H. Ney , Philips GmbH Res. Lab., Aachen, Germany
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%.
INDEX TERMS
CITATION

R. Haeb-Umbach, H. Ney and D. Geller, "Improvements in connected digit recognition using linear discriminant analysis and mixture densities," Acoustics, Speech, and Signal Processing, IEEE International Conference on(ICASSP), Minneapolis, MN, USA, 1993, pp. 239-242.
doi:10.1109/ICASSP.1993.319279
88 ms
(Ver 3.3 (11022016))