The week's pick
Reseach Article
Text Independent Speaker Identification with Finite Multivariate Generalized Gaussian Mixture Model with Distant Microphone Speech
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 14 - Number 4 |
| Year of Publication: 2011 |
| Authors: K.Jyothi, Dr.V Sailaja, Dr.K. Srinivasa Rao |
10.5120/1835-2463
|
K.Jyothi, Dr.V Sailaja, Dr.K. Srinivasa Rao . Text Independent Speaker Identification with Finite Multivariate Generalized Gaussian Mixture Model with Distant Microphone Speech. International Journal of Computer Applications. 14, 4 ( January 2011), 5-9. DOI=10.5120/1835-2463
Abstract
An effective and efficient speaker Identification (SI) system requires a robust feature extraction module followed by a speaker modeling scheme for generalized representation of these features. In recent, years Speaker Identification has seen significant advancement, but improvements have tended to be bench marked on the near field speech, ignoring the more realistic setting of far field instrumented speaker. A novel speaker model is developed by using Finite Multivariate Generalized Gaussian Mixture Model, Minimum Variance Distortion less Response Cepstral coefficients as feature Vectors. The performance of the developed model is studied through experimental evaluation with 45 speaker’s data base and identification accuracy.
References
- Armando. J et al (2003), “A practical procedure to estimate the shape Parameters in the Generalized Gaussian distribution.
- Ben Gold and Nelson Morgan (2002), “Speech and Audio Processing”, Part IV , Chapter 14,pp 189 – 203 , John willy and sons.
- Douglas A. Reynolds, member, IEEE and Richard C.Rose, Member, IEEE ‘Robust text- Independent Speaker Identification Using Gaussian Mixture Speaker Models’
- EL-Jaroudi,A. and Makhoul,J (1991)” Discrete all- pole modelling” .IEEE rans. Speech Processing, vol.39:pp.411- 423.
- J.P. Cambell. Jr(1997).”Speaker Recognition: A Tutorial”, Processing of the IEEE, vol.85, no9, pp. 1437-1462..
- Md M. Bicego, D Gonzalez, E Grosso and Alba Castro (2008) “Generalized Gaussian distribution for sequential Data Classification” IEEE Trans. 978 -1- 4244-2175-6.
- Md.Rashidul Hasan, Mustafa Jamil, Md Golam Rabbani Md.Saifar Rahman (2004) “Speaker identification using Mel frequency cepstral coefficients” ICECE 2004,28-30 December ,ISBN 984- 32-1804-4,pp 565 to568.
- Qin Jin ,Ruxxin Li,Qian Yang,Kornel Laskowski, Tanja Schultz (2010). ‘Speaker Identification with Distant Microphone Speech’ IEEE978-1-4244-4296-6/10.
- Rabiner .Ljuang B.H(2003) ”fundamentals of speech reconition”,Chap.2,pp.11-65, Pearson Education, First Indian reprint.
- R.Vergin,B.OShaughnessy and a.Farhat(Sep.1999) “Generalize Mel frequency cepstral coefficient for large-vocabulary speaker independent continuous speech recognition, IEEE Trans.OnASSP,vol.7,no 5,pp.525-532,.
- Sandipan Chakraborthy, Anindya Roy and Goutam Saha (2006) “Improved Closed Set text-Independent Speaker identification by combining MFcc with Evidence from Flipped Filter banks’IJSp vol 4,no 2
- Sharif k etal(1995), “Estimation of shape parameters for generalized Gaussian Distribution in Sub band decomposition or video”, IEEE transaction on circuit systems vol.5 no.1 pp. 52-56.
- U.G.Goldstein(1976.) ”speaker Identifying features based on formant tracks” J.Acoust, Soc.am, vol.59, No.1,pp.176- 182.
- Varanasi.MK et al(1989), “Parametric generalized Gaussian densit Estimation”, Journal Acoust. Soc.AM 86(4) pp. 1404.
- Wu.H.C.Y Principe J (1998), “Minimum entropy algorithm for source separation” proceedings of the Midwest symposium on system and circuits.
Index Terms
Keywords