Advertisement

The CLEAR’06 LIMSI Acoustic Speaker Identification System for CHIL Seminars

  • Claude Barras
  • Xuan Zhu
  • Jean-Luc Gauvain
  • Lori Lamel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4122)

Abstract

This paper summarizes the LIMSI participation in the CLEAR’06 acoustic speaker identification task that aims to identify speakers in CHIL seminars via the acoustic channel. The system consists of a standard Gaussian mixture model based system similar to systems developed for the NIST speaker recognition evaluations and includies feature warping of cepstral coefficients and MAP adaptation of a Universal Background Model. Several computational optimizations were implemented for real-time efficiency: stochastic frame subsampling for training, top-Gaussians scoring and auto-adaptive pruning for the tests, speeding up the system by more than a factor of ten.

Keywords

Target Model Speaker Recognition Microphone Array Test Segment Universal Background Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barras, C., Gauvain, J.-L.: Feature and score normalization for speaker verification of cellular data. In: Proc. of IEEE ICASSP (May 2003)Google Scholar
  2. 2.
    Doddington, G., Przybocki, M., Martin, A., Reynolds, D.: The NIST speaker recognition evaluation - overview, methodology, systems, results, perspective. Speech Communication 31, 225–254 (2000)CrossRefGoogle Scholar
  3. 3.
    Gauvain, J.-L., Lee, C.H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing 2(2), 291–298 (1994)CrossRefGoogle Scholar
  4. 4.
    McLaughlin, J., Reynolds, D., Gleason, T.: A Study of Computation Speed-UPS of the GMM-UBM Speaker Recognition System. In: Proc. Eurospeech’99, Budapest, pp. 1215–1218 (Sept. 1999)Google Scholar
  5. 5.
    Mostefa, D., et al.: CLEAR Evaluation Plan v1.1 (2006), http://isl.ira.uka.de/clear06/downloads/chil-clear-v1.1-2006-02-21.pdf
  6. 6.
    Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. In: Proc. ISCA Workshop on Speaker Recognition - Odyssey (June 2001)Google Scholar
  7. 7.
    Reynolds, D., Quatieri, T., Dunn, R.: Speaker verification using adapted Gaussian mixture models. Digital Signal Processing 10, 19–41 (2000)CrossRefGoogle Scholar
  8. 8.
    Zhu, X., Leung, C-C., Barras, C., Lamel, L., Gauvain, J-L.: Speech activity detection and speaker identification for CHIL. In: Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI), Edinburgh (July 2005)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Claude Barras
    • 1
  • Xuan Zhu
    • 1
  • Jean-Luc Gauvain
    • 1
  • Lori Lamel
    • 1
  1. 1.Spoken Language Processing Group, LIMSI-CNRS, BP 133, 91403 Orsay cedexFrance

Personalised recommendations