Now showing items 1-10 of 10

  • Detection of Target Speakers in Audio Databases 

    Magrin-Chagnolleau, Ivan; Rosenberg, Aaron; Parthasarathy, S. (1999-01-15)
    The problem of speaker detection in audio databases is addressed in this paper. Gaussian mixture modeling is used to build target speaker and background models. A detection algorithm based on a likelihood ratio calculation ...
  • Effect of Utterance Duration and Phonetic Content on Speaker Identification Usind Second Order Statistical Methods 

    Magrin-Chagnolleau, Ivan; Bonastre, Jean-Francois; Bimbot, Frederic (1995-01-01)
    Second-order statistical methods show very good results for automatic speaker identification in controlled recording conditions. These approaches are generally used on the entire speech material available. In this paper, ...
  • Empirical Mode Decomposition Based Frequency Attributes 

    Magrin-Chagnolleau, Ivan; Baraniuk, Richard G. (1999-11-01)
    This paper describes a new technique, called <i>Empirical Mode Decomposition</i> (EMD), which allows the decomposition of one-dimensional signals into intrinsic oscillatory modes. Each component, called <i>Intrinsic Mode ...
  • A Further Investigation on AR-Vector Models for Text Independent Speaker Identification 

    Magrin-Chagnolleau, Ivan; Bimbot, Frederic (1996-01-01)
    In this paper, we investigate on the role of dynamic information on the performances of AR-vector models for speaker recognition. To this purpose, we design an experimental protocol that destroys the time structure of ...
  • Multiscale Texture Segmentation of Dip-cube Slices using Wavelet-domain Hidden Markov Trees 

    Magrin-Chagnolleau, Ivan; Choi, Hyeokho; van Spaendonck, Rutger; Steeghs, Philippe; Baraniuk, Richard G. (1999-11-01)
    Wavelet-domain Hidden Markov Models (HMMs) are powerful tools for modeling the statistical properties of wavelet coefficients. By characterizing the joint statistics of wavelet coefficients, HMMs efficiently capture the ...
  • An Overview of the AT&T Spoken Document Retrieval System 

    Choi, John; Hindle, Don; Hirschberg, Julia; Magrin-Chagnolleau, Ivan; Nakatani, Christine; Pereira, Fernando; Singhal, Amit; Whittaker, Steve (1998-01-15)
    We present an overview of a spoken document retrieval system developed at AT&T Labs-Research for the HUB4 Broadcast News corpus. This overview includes a description of the intonational phrase boundary detection, ...
  • SCAN - Speech Content Based Audio Navigator: A Systems Overview 

    Choi, John; Hindle, Don; Hirschberg, Julia; Magrin-Chagnolleau, Ivan; Nakatani, Christine; Pereira, Fernando; Singhal, Amit; Whittaker, Steve (1998-01-15)
    SCAN (Speech Content based Audio Navigator) is a spoken document retrieval system integrating speaker-independent, large-vocabulary speech recognition with information-retrieval to support query-based retrieval of information ...
  • Second-Order Statistical Measures for Text-Independent Speaker Identification 

    Bimbot, Frederic; Magrin-Chagnolleau, Ivan (1995-08-20)
    This article presents an overview of several measures for speaker recognition. These measures relate to second-order statistical tests, and can be expressed under a common formalism. Alternate formulations of these measures ...
  • Speaker Detection in Broadcast Speech Databases 

    Rosenberg, Aaron; Magrin-Chagnolleau, Ivan; Parthasarathy, S. (1998-01-15)
    Experiments have been carried out to assess the feasibility of detecting target speaker segments in multi-speaker broadcast databases. The experiemental database consists of NBC Nightly News broadcasts. The target speaker ...
  • Time Frequency Principal Components: Application to Speaker Identification 

    Magrin-Chagnolleau, Ivan; Durou, Geoffrey (1999-01-01)
    In this paper, we propose a formalism, called vector filtering of spectral trajectories, which allows to integrate under a common formalism a lot of speech parameterization approaches. We then propose a new filtering in ...