Parallel Implementation of a VQ-Based Text-Independent Speaker Identification
This study presents parallel implementation of a vector quantization (VQ) based text-independent speaker identification system that uses Melfrequency cepstrum coefficients (MFCC) for feature extraction, Linde-Buzo-Gray (LBG) VQ algorithm for pattern matching and Euclidean distance for match score calculation. Comparing meaningful characteristics of voice samples and matching them with similar ones requires large amount of transformations and comparisons, which result in large memory usage and disk access. When the cost of computations is considered, it states the main motivation for a parallel speaker identification implementation, where the parallelism is achieved using domain decomposition. In this paper, we present a set of experiments using the YOHO speaker corpus and observe the effects of several parameters as VQ size, number of MFCC filter banks and threshold value. First we focus on the serial algorithm and improve the algorithm to give the best success rates and provide a strong base for parallel implementation, where a clear performance improvement on speedup is obtained.
KeywordsGaussian Mixture Model Filter Bank Message Passing Interface Parallel Implementation Vector Quantization
Unable to display preview. Download preview PDF.
- 1.Campbell, J.P.: Speaker Recognition: A Tutorial. Proceedings of the IEEE 85(9) (September 1997)Google Scholar
- 2.Quatieri, T.F.: Discrete-Time Speech Signal Processing: Principles and Practice. Prentice Hall, Englewood Cliffs (2001)Google Scholar
- 3.Furui, S.: Digital Speech Processing, Synthesis and Recognition (February 2001) ISBN: 0824704525Google Scholar
- 4.James, D., Hutter, H.P., Bimbot, F.: The CAVE Speaker Verification Project-Experiments on the YOHO and SESP corpora. In: 1st Inernational Conf. On AVBPA, Crans-Montana, Switzerland (1997)Google Scholar
- 5.Pellom, B., Hansen, J.: An Efficient Scoring Algorithm for GMM based Speaker Identification. IEEE Signal Processing Letters 5(11), 281–284Google Scholar
- 6.Park, A., Hazen, J.: ASR Dependent Techniques For Speaker Identification. In: Proceedings of the 7th Internatonal Conference on Spoken Kanguage Processing, Denver, Colorado, September 16-20, pp. 1337–1340 (2002)Google Scholar
- 7.Zilca, R.D.: Text-independent speaker verification using covariance modeling. IEEE Signal Processing Letters 8(4) (April 2001)Google Scholar
- 8.MPITB (2004), http://atc.ugr.es/javier-bin/mpitb_eng
- 9.MultiMatlab (2004), http://www.cs.cornell.edu/Info/People/lnt/multimatlab.html