Locally Recurrent Probabilistic Neural Networks with Application to Speaker Verification

To improve speaker verification performance, we extend the well- known Probabilistic Neural Networks (PNN) to Locally Recurrent Probabilistic Neural Networks (LRPNN). In contrast to PNNs that possess no feedbacks, LRPNNs incorporate internal connections to the past outputs of all recurrent neurons, which render them sensitive to the context in which events occur. Thus, LRPNNs are capable of identifying time and spatial correlations. A fast three-step method is proposed for training an LRPNN. The first two steps are identical to the training of traditional PNNs, whil e the third step is based on the Differential Evolution optimization method. The per formance of the proposed LRPNNs is compared with that of the PNNs on the task of text-independent speaker verification.

[1]  Joseph Bibb Cain.  Improved probabilistic neural network and its performance relative to other models , 1990, Defense, Security, and Sensing.

[2]  Dominique Genoud,et al.  POLYCOST: A telephone-speech database for speaker recognition , 2000, Speech Commun..

[3]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[4]  Michael R. Berthold,et al.  Constructive training of probabilistic neural networks , 1998, Neurocomputing.

[5]  Robert B. Ash,et al.  Information Theory , 2020, The SAGE International Encyclopedia of Mass Media and Society.

[6]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[7]  Nicos G. Pavlidis,et al.  Optimizing the Performance of Probabilistic Neural Networks in a BioinformaticsTa sk , 2004 .

[8]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[9]  B. Atal.  Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. , 1974, The Journal of the Acoustical Society of America.

[10]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[11]  Dimitris K. Tasoulis,et al.  Locally recurrent probabilistic neural network for text-independent speaker verification , 2003, INTERSPEECH.

[12]  Todor Ganchev,et al.  TEXT-INDEPENDENT SPEAKER VERIFICATION BASED ON PROBABILISTIC NEURAL NETWORKS , 2002 .

[13]  Mahmood R. Azimi-Sadjadi,et al.  Temporal updating scheme for probabilistic neural network with application to satellite cloud classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[15]  Sheng Chen,et al.  Robust maximum likelihood training of heteroscedastic probabilistic neural networks , 1998, Neural Networks.

[16]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[17]  Sun-Yuan Kung,et al.  Estimation of elliptical basis function parameters by the EM algorithm with application to speaker verification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[18]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[19]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[20]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[21]  H Hermansky,et al.  Perceptual linear predictive (PLP) analysis of speech. , 1990, The Journal of the Acoustical Society of America.

[22]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[23]  D. F. Specht,et al.  Enhancements to probabilistic neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[24]  William S. Meisel,et al.  Computer-oriented approaches to pattern recognition , 1972 .

[25]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .