Linear discriminant analysis for improved large vocabulary continuous speech recognition
Authors:
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 13-16 vol.1
Abstract
The interaction of linear discriminant analysis (LDA) and a modeling approach using continuous Laplacian mixture density HMM is studied experimentally. The largest improvements in speech recognition could be obtained when the classes for the LDA transform were defined to be sub-phone units. On a 12000 word German recognition task with small overlap between training and test vocabulary a reduction in error rate by one-fifth was achieved compared to the case without LDA. On the development set of the DARPA RM1 task the error rate was reduced by one-third. For the DARPA speaker-dependent no-grammar case, the error rate averaged over 12 speakers was 9.9%. This was achieved with a recognizer using LDA and a set of only 47 Viterbi-trained context-independent phonemes.<>Keywords
This publication has 5 references indexed in Scilit:
- Acoustic-phonetic transformations for improved speaker-independent isolated word recognition1991
- The Lincoln tied-mixture HMM continuous speech recognizer1991
- An investigation of PLP and IMELDA acoustic representations and of their potential for combination1991
- Improved vocabulary-independent sub-word HMM modelling1991
- The Acoustic-Modeling Problem in Automatic Speech Recognition.1987