Speaker recognition in reverberant environments

Auteurs-es

  • Joseph Gammal Dept. of Systems Engineering, Carleton University, Colonel By Dr., Ottawa, K1S 5B6, Canada
  • Rafik Goubran Dept. of Systems Engineering, Carleton University, Colonel By Dr., Ottawa, K1S 5B6, Canada

Mots-clés :

Computer simulation, Database systems, Impulse response, Matrix algebra, Microphones, Natural frequencies, Reverberation, Signal processing, Vectors, Gaussian mixture models (GMM), Reflection coefficients, Sampling frequency, Speaker recognition

Résumé

The comparison of the methods used for the purpose of speaker recognition and parametrizations, when there is a mismatch between training and test conditions due to reverberation, was discussed. Gaussian mixture models (GMM), covariance models, and AR-vector models were used for this purpose. It was fond that the performance of all the methods degrades under reverberation. It was also found that recognition accuracy improved for all the methods when training was performed with reverberant speech prior to testing with minor reverb or major reverb.

Fichiers supplémentaires

Publié-e

2004-09-01

Comment citer

1.
Gammal J, Goubran R. Speaker recognition in reverberant environments. Canadian Acoustics [Internet]. 1 sept. 2004 [cité 13 févr. 2025];32(3):134-5. Disponible à: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/1664

Numéro

Rubrique

Actes du congrès de la Semaine canadienne d'acoustique