TITLE

SPEAKER RECOGNITION MODEL BASED ON GENERALIZED GAMMA DISTRIBUTION USING COMPOUND TRANSFORMED DYNAMIC FEATURE VECTOR

AUTHOR(S)
Babu, K. Suri; Yarramalle, Srinivas; Penumatsa, Suresh Varma
PUB. DATE
September 2012
SOURCE
International Journal of Embedded Systems & Applications;Sep2012, Vol. 2 Issue 3, p75
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
In this paper, we present an efficient speaker identification system based on generalized gamma distribution. This system comprises of three basic operations, namely speech features classification and metrics for evaluation. The features extracted using MFCC are passed to shifted delta cepstral coefficients (SDC) and then applied to linear predictive coefficients (LPC) to have effective recognition. To demonstrate our method, a database is generated with 200 speakers for training and around 50 speech samples for testing. Above 90% accuracy reported.
ACCESSION #
82442400

 

Related Articles

  • Calculation of 237Np and 241Am detector calibration constants from first principles. Dewberry, R. A. // Journal of Radioanalytical & Nuclear Chemistry;Dec2004, Vol. 262 Issue 3, p783 

    The Analytical Development Section of Savannah River Technology Center (SRTC) was requested by the Facilities Disposition Projects (FDP) to determine the holdup of enriched uranium in the 321-M facility as part of an overall deactivation project of the facility. The 321-M facility was used to...

  • An Analytical Approach to Outage Analysis and Critical Cooperation Ratio in Coded Cooperation. Bansal, Ankur; Garg, Parul // Wireless Personal Communications;Mar2013, Vol. 69 Issue 2, p721 

    In this paper, we analyze the performance of a coded cooperation based communication system using independent flat Nakagami- m fading channels. We examine the outage behavior of the cooperative system constrained on instantaneous received power which follows the Gamma distribution. The...

  • Text Dependent and Gender Independent Speaker Recognition Model based on Generalizations of Gamma Distribution. Babu, K. Suri; Penumatsa, Suresh Varma; Yarramalle, Srinivas; Vadaparthi, Nagesh // International Journal of Computer Applications;Dec2011, Vol. 35, p1 

    Speaker recognition is one of the research potential areas with applications in biometrics and content based retrievals, it helps to identify a speaker from the speech signal. To develop an effective speaker recognition system, it is needed to have a concrete methodology of feature extraction...

  • PC-Based System for Gamma Mapping.  // Physics Today;Apr89, Vol. 42 Issue 4, p87 

    Reviews MPA/PC, a PC-based multiparameter system from Cranberra.

  • OmniBus opens to Web. Fox, David // TVB Europe;Mar99, Vol. 8 Issue 3, p14 

    Reports on the plan of OmniBus to open its systems to the Web with GAMMA (Global Asset and Media Management Applications). Reasons behind the move; Role of GAMMA in getting access to archives.

  • Development of a Digital Signal Readout System for Large TES Arrays. W. Hennig; H. Tan; T. Niedermayr; D. Breus; O. Drury; W. Warburton; S. Friedrich // Journal of Low Temperature Physics;May2008, Vol. 151 Issue 3/4, p958 

    Abstract  We are developing a digital signal readout system for arrays of high-resolution gamma and fast-neutron detectors based on superconducting transition edge sensors (TESs). The readout system allows for real time data acquisition and analysis at count rates exceeding 100...

  • The Year Of Peer. Spangler, Todd // Interactive Week;1/8/2001, Vol. 8 Issue 1, p68 

    Looks at the status of peer-to-peer (P2P) computing in 2001. Advantages of P2P computing; Expectations of technology enthusiasts about the potential of P2P computing; Actions taken by computer system manufacturers to improve P2P computing; Implications of the emergence of P2P computing.

  • Effective Fault Diagnosis Approaches for Multipath Networks. Po-Jen Chuang; Huey-Ming Hsu // Computer Journal;Jul1999, Vol. 42 Issue 5, p409 

    Fault diagnosis is important for the immediate elimination of faults in a network. Over the years the diagnosis of faults for a single path network is frequently reported but that for a multipath network remains relatively unattended. The goal of this research is to detect faults in the gamma...

  • Advantages of the D2 Statistic. Burden, C. J.; Jing, J.; Wilson, S. R. // Annual International Conference on Bioinformatics & Computationa;Mar2011, pB18 

    The D2 statistic, defined as the number of matches of words of some pre-specified length k, is a computationally fast alignment-free measure of biological sequence similarity. However there is some debate about its suitability for this purpose as it may be susceptible to single-sequence noise....

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics