Speaker recognition and speaker normalization by projection to speaker subspace

Authors:
Y. Ariki;S. Tagashira;M. Nishijima
Affiliations:
Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan;Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan;Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan
Venue:
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Year:
1996

Citing 0
Cited 5

Efficient speaker identification based on robust VQ-PCA

ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartII
A global covariance matrix based principal component analysis for speaker identification

APCC'09 Proceedings of the 15th Asia-Pacific conference on Communications
Common vector approach and its combination with GMM for text-independent speaker recognition

Expert Systems with Applications: An International Journal
Speaker verification and identification using principal component analysis based on global eigenvector matrix

HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
i-Vector with sparse representation classification for speaker verification

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

An individual speaker is thought to have his own subspace in which his phonetic information is included. However, conventional speaker-independent HMMs ignore the speaker subspaces and gather speech data spread widely in the observation space. Then they cause probability distribution flatness of HMMs and the resultant recognition errors. To solve this problem, we propose a method (1) to separate the speaker characteristics by constructing the individual speaker subspace, (2) to recognize speakers based on the subspaces and (3) to produce speaker normalized speech data by projecting speech data into his subspace and to recognize them.