TY - GEN
T1 - Discriminative algorithm for compacting mixture models with application to language recognition
AU - Bar-Yosef, Yossi
AU - Bistritz, Yuval
PY - 2012
Y1 - 2012
N2 - In this paper we explore a discriminative algorithm for compacting large order mixture models. Several studies investigated efficient algorithms for finding a reduced-order model that best approximates a referenced model using only the original mixture parameters. Recently, a discriminative approach named maximum correct association (MCA) was introduced to efficiently construct a set of compact models for improved classification. In this paper we suggest a two stage procedure that applies the MCA algorithm after initially obtaining a compact model through the variational-EM method (which is a non-discriminative algorithm). The proposed method is validated in a language recognition task where large order mixture models are compacted into low order models. Experiments showed that the MCA-refined models performed consistently better than reduced models derived with the non-discriminative methods including boosting performance over the standard maximum-likelihood trained from the original data.
AB - In this paper we explore a discriminative algorithm for compacting large order mixture models. Several studies investigated efficient algorithms for finding a reduced-order model that best approximates a referenced model using only the original mixture parameters. Recently, a discriminative approach named maximum correct association (MCA) was introduced to efficiently construct a set of compact models for improved classification. In this paper we suggest a two stage procedure that applies the MCA algorithm after initially obtaining a compact model through the variational-EM method (which is a non-discriminative algorithm). The proposed method is validated in a language recognition task where large order mixture models are compacted into low order models. Experiments showed that the MCA-refined models performed consistently better than reduced models derived with the non-discriminative methods including boosting performance over the standard maximum-likelihood trained from the original data.
KW - Gaussian mixture models
KW - discriminative learning
KW - hierarchical clustering
KW - language recognition
UR - http://www.scopus.com/inward/record.url?scp=84869752493&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84869752493
SN - 9781467310680
T3 - European Signal Processing Conference
SP - 2203
EP - 2207
BT - Proceedings of the 20th European Signal Processing Conference, EUSIPCO 2012
T2 - 20th European Signal Processing Conference, EUSIPCO 2012
Y2 - 27 August 2012 through 31 August 2012
ER -