BDBComp
Parceria:
SBC
Identificação de locutor independente do texto baseada em Vetores de Hurst e no Classificador M_dim_f Bm

R. Sant´anaR. CoelhoA. Alcaim

The performance of Hurst-Vectors (pH feature) and the M_dim_f Bm (Multi-dimensional fractional Brownian motion) classifier for speaker identification system is present in this paper. The pH feature is a vector of Hurst parameters obtained by applying a wavelet-based multi-dimensional estimator (M_dim_wavelets) to the windowed short-time segments of speech. The GMM (Gaussian Mixture Models), the AR-Vector and the dB (Battacharya distance) classification systems were also considered in the performance analysis. The speech database - recorded from fixed and cellular phone channels - was uttered by 75 diferent speakers. The results have shown the superior performance of the M_dim_f Bm classifier and the pH feature aggregates new information on the speaker identity.

http://www.lbd.dcc.ufmg.br/colecoes/til/2005/001.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD