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: 648-651
X. Aubert , Philips GmbH Res. Lab., Aachen, Germany
R. Haeb-Umbach , Philips GmbH Res. Lab., Aachen, Germany
H. Ney , Philips GmbH Res. Lab., Aachen, Germany
ABSTRACT
Linear discriminant analysis (LDA) experiments reported previously (ICASSP-92 vol.1, p.13-16), are extended to context-dependent models and speaker-independent large vocabulary continuous speech recognition. Two variants of using mixture densities are compared: state-specific modeling and the monophone-tying approach where densities are shared across the states relevant to the same phoneme. Results are presented on the DARPA Resource Management (RM) task for both speaker-dependent (SD) and speaker-independent (SI) parts. Using triphone models based on LDA and continuous mixture densities, significant improvements have been observed and the following word error rates have been achieved: for the SD part, 7.8% without grammar and 1.5% with word pair; and for the SI part, 17.2% and 4.6%, respectively. These scores are averaged over 1200 SD or SI evaluation sentences and are among the best published so far on the RM database.
INDEX TERMS
CITATION

R. Haeb-Umbach, X. Aubert and H. Ney, "Continuous mixture densities and linear discriminant analysis for improved context-dependent acoustic models," Acoustics, Speech, and Signal Processing, IEEE International Conference on(ICASSP), Minneapolis, MN, USA, 1993, pp. 648-651.
doi:10.1109/ICASSP.1993.319393
97 ms
(Ver 3.3 (11022016))