TY - GEN
T1 - Adaptive score fusion using weighted logistic linear regression for spoken language recognition
AU - Sim, Khe Chai
AU - Lee, Kong Aik
PY - 2010
Y1 - 2010
N2 - State-of-the-art spoken language recognition systems typically consist of a combination of sub-systems. These subsystems generate language detection scores for each speech segment, which will be fused (combined) to yield the overall detection scores. Typically, score fusion is achieved using a linear model and Logistic Linear Regression (LLR) is commonly used to estimate the model parameters. This paper proposes an extension to the LLR model, known as the Weighted LLR (WLLR). WLLR is obtained using a weighted combination of multiple LLRs where the weights are obtained as a nonlinear function of the speech segments. Although the resultant score is still linear with respect to the scores of the individual sub-systems, the linear function depends on the speech segment. Hence, the overall score fusion model can be regarded as an adaptive model. Experimental results shows that WLLR outperforms LLR by approximately 10% relative for PPRLM system fusion on the NIST 2003 and 2005 language recognition evaluation sets.
AB - State-of-the-art spoken language recognition systems typically consist of a combination of sub-systems. These subsystems generate language detection scores for each speech segment, which will be fused (combined) to yield the overall detection scores. Typically, score fusion is achieved using a linear model and Logistic Linear Regression (LLR) is commonly used to estimate the model parameters. This paper proposes an extension to the LLR model, known as the Weighted LLR (WLLR). WLLR is obtained using a weighted combination of multiple LLRs where the weights are obtained as a nonlinear function of the speech segments. Although the resultant score is still linear with respect to the scores of the individual sub-systems, the linear function depends on the speech segment. Hence, the overall score fusion model can be regarded as an adaptive model. Experimental results shows that WLLR outperforms LLR by approximately 10% relative for PPRLM system fusion on the NIST 2003 and 2005 language recognition evaluation sets.
KW - Fusion
KW - Language recognition
KW - Logistic linear regression
KW - PPRLM
UR - http://www.scopus.com/inward/record.url?scp=78049363530&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2010.5495069
DO - 10.1109/ICASSP.2010.5495069
M3 - Conference article published in proceeding or book
AN - SCOPUS:78049363530
SN - 9781424442966
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5018
EP - 5021
BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Y2 - 14 March 2010 through 19 March 2010
ER -