Robust Speaker Recognition in Noisy Environments: Using Dynamics of Speaker-Specific Prosody

Koolagudi, Shashidhar G.; Rao, K. Sreenivasa; Reddy, Ramu; Kumar, Vuppala Anil; Chakrabarti, Saswat

doi:10.1007/978-1-4614-0263-3_8

Cited by 5 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaussian Mixture Models (GMM) is conventional and successful method for the speaker recognition approach (El Hannani & Petrovska-Delacrétaz, 2005;Garcia et al, 2007;Koolagudi et al, 2011;Reynolds & Rose, 1995;Wahid et al, in press). A Gaussian mixture density is a weighted sum of M component densities and is given by:…”

Section: Gaussian Mixture Model: Preliminariesmentioning

confidence: 99%

Heart Sounds Human Identification and Verification Approaches using Vector Quantization and Gaussian Mixture Models

Ghali

Wahid

Hassanien

2012

International Journal of Systems Biology and Biomedical Technologies

View full text Add to dashboard Cite

In this paper the possibility of using the human heart sounds as a human print is investigated. To evaluate the performance and the uniqueness of the proposed approach, tests using a high resolution auscultation digital stethoscope are done for nearly 80 heart sound samples. The verification approach consists of a robust feature extraction with a specified configuration in conjunction with Gaussian mixture modeling. The similarity of two samples is estimated by measuring the difference between their negative log-likelihood similarities of the features. The experimental results obtained show that the overall accuracy offered by the employed Gaussian mixture modeling reach up to 85%. The identification approach consists of a robust feature extraction with a specified configuration in conjunction with LBG-VQ. The experimental results obtained show that the overall accuracy offered by the employed LBG-VQ reach up to 88.7%.

show abstract

Section: Gaussian Mixture Model: Preliminariesmentioning

confidence: 99%