A piecewise linear spectral mapping for supervised speaker adaptation
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 449-452 vol.1
- https://doi.org/10.1109/icassp.1992.225875
Abstract
A supervised spectral mapping method for speaker adaptation based on a piecewise linear transformation of cepstral vectors is proposed. In this method, an input vector is mapped onto the target spectral space by a weighted sum of linearly transformed vectors using a set of mapping matrices which are associated with fuzzy partitioned spaces. These matrices were estimated so as to minimize the total mean square error between the mapped and target spectra. This method was compared with the difference interpolation mapping (D-map) method, which is an extension of the codebook mapping methods. Through 16 phoneme recognition tests using a single Gaussian distribution hidden Markov model (HMM), it was found that the proposed method with 16 fuzzy partitioned spaces improved recognition performance by 4% compared to the usual linear mapping method when using 100 training words, and also achieved a 3% higher rate on average than the D-map method.Keywords
This publication has 8 references indexed in Scilit:
- Rapid speaker adaptation using a probabilistic spectral mappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speaker adaptation through vector quantizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Improved speaker adaption using text dependent spectral mappingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A comparative study of spectral mapping for speaker adaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fast speaker adaptation for speech recognition systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker adaptation of a code book of vector quantization.Acoustical Science and Technology, 1988
- Pattern Recognition with Fuzzy Objective Function AlgorithmsPublished by Springer Nature ,1981
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974