Browsing by Author "Huenupán, Fernando"

Now showing items 1-4 of 4

    • Confidence based multiple classifier fusion in speaker verification 
      Huenupán, Fernando; Becerra Yoma, Néstor; Molina, Carlos; Garretón, Claudio (ELSEVIER, 2008-05-01)
      A novel framework that applies Bayes-based confidence measure for multiple classifier system fusion is proposed. Compared with ordinary Bayesian fusion, the presented approach can lead to reductions as high as 37% and 35% ...
    • On Reducing Harmonic and Sampling Distortion in Vocal Tract Length Normalization 
      Becerra Yoma, Néstor; Garretón, Claudio; Huenupán, Fernando; Catalán, Ignacio; Wuth Sepúlveda, Jorge (2013)
      This paper proposes a novel feature-space VTLN (vocal tract length normalization) method that models frequency warping as a linear interpolation of contiguous Mel filter-bank energies. The presented technique aims to ...
    • A perceptually-motivated low-complexity instantaneous linearchannel normalization technique applied to ... 
      Poblete Ramírez, Víctor; Espic, Felipe; King, Simon; Stern, Richard M.; Huenupán, Fernando; Fredes Sandoval, Josué Abraham; Becerra Yoma, Néstor (Elsevier, 2015)
      This paper proposes a new set of speech features called Locally-Normalized Cepstral Coefficients (LNCC) that are based onSeneff’s Generalized Synchrony Detector (GSD). First, an analysis of the GSD frequency response is ...
    • Unsupervised intra-speaker variability compensation based on Gestalt and model adaptation in speaker ... 
      Becerra Yoma, Néstor; Garretón, Claudio; Molina, Carlos; Huenupán, Fernando (ELSEVIER, 2008-11)
      In this paper, an unsupervised intra-speaker variability compensation (ISVC) method based oil Gestalt is proposed to address the problem of limited enrolling data and noise robustness in text-dependent speaker verification ...