Discriminative likelihood score weighting based on acoustic-phonetic classification for speaker identification

被引：0
作者：
Youngjoo Suh
Hoirin Kim
机构：
[1] Korea Advanced Institute of Science and Technology,Department of Electrical Engineering
来源：
EURASIP Journal on Advances in Signal Processing | / 2014卷
关键词：
Discriminative training; Acoustic-phonetic classification; Score weighting; Speaker identification;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, a new discriminative likelihood score weighting technique is proposed for speaker identification. The proposed method employs a discriminative weighting of frame-level log-likelihood scores with acoustic-phonetic classification in the Gaussian mixture model (GMM)-based speaker identification. Experiments performed on the Aurora noise-corrupted TIMIT database showed that the proposed approach provides meaningful performance improvement with an overall relative error reduction of 15.8% over the maximum likelihood-based baseline GMM approach.
引用
收藏
相关论文
共 38 条
[1]  
Reynolds DA(1995)Robust text-independent speaker identification using Gaussian mixture speaker models IEEE Trans. Speech Audio Process 3 72-83
[2]  
Rose RC(2006)Support vector machines using GMM supervectors for speaker verification IEEE Signal. Proc. Let 13 308-311
[3]  
Campbell WM(2006)Real-time speaker identification and verification IEEE Trans. Audio Speech Lang. Process 14 277-281
[4]  
Sturim DE(2000)Speaker verification using adapted Gaussian mixture models Digital Signal. Process 10 19-41
[5]  
Reynolds DA(1995)A study on minimum error discriminative training for speaker recognition J. Acoust. Soc. Am 97 637-648
[6]  
Kinnunen T(2011)Front-end factor analysis for speaker verification IEEE Trans. Audio Speech Lang. Process 19 788-798
[7]  
Karpov E(2013)Minimum classification error-based weighted support vector machine kernels for speaker verification J. Acoust. Soc. Am 133 EL307-EL313
[8]  
Fränti P(2010)Robust speaker recognition based on filtering in autocorrelation domain and sub-band feature recombination Pattern Recognition Lett 31 593-599
[9]  
Reynolds DA(2007)Probabilistic class histogram equalization for robust speech recognition IEEE Signal Proc. Let 14 287-290
[10]  
Quatieri TF(1992)Discriminative learning for minimum error classification IEEE Trans. Signal Process 40 3043-3054
1234