Combined inter-frame and intra-frame fast scoring methods for efficient implementation of GMM-based speaker verification systems

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 4, Issue , 2007, Pages

  Sadegh Mohammadi, H R ^a   Saeidi, R ^b   Rohani, M R ^b   Rodman, R D ^c  

^a Iranian Research Institute for Electrical Engineering   (Iran)

^b Research Center of Intelligent Signal Processing   (Iran)

^c North Carolina State University   (United States)

Author keywords

Decimation; Fast scoring; GMM UBM; Speaker verification; Speed up

Indexed keywords

BLOCKING PROBABILITY; COMPUTATIONAL EFFICIENCY; MATHEMATICAL MODELS; PROBLEM ORIENTED LANGUAGES; SORTING;

GAUSSIAN MIXTURE MODEL (GMM); INTER-FRAME FAST SCORING; SORTED GAUSSIAN MIXTURE MODEL (SGMM); SPEAKER VERIFICATION SYSTEMS;

SPEECH INTELLIGIBILITY;

EID: 34547538197     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.366911     Document Type: Conference Paper

References (10)

1. D. A. Reynolds, T F. Quatieri, and R B. Dunn, "Speaker verification using adapted Gaussian mixture models," Digital Signal Processing, vol. 10, no. 1-3, pp. 19-41, Jan. 2000.
2. J. Mclaughlin, D. A. Reynolds, and T. Gleason, "A study of computation speed-ups of the GMM-UBM speaker recognition system," in Proc. Eurospeech '99, pp. 1215-1218, 1999.
3. K. Shinoda and C. H. Lee, "A structural Bayes approach to speaker adaptation," IEEE Trans. Speech Audio Processing, vol. 9, no. 3, pp. 276-287, May 2001.
4. B. Xiang and T. Berger, "Efficient text-independent speaker verification with structural Gaussian mixture models and neural networks," IEEE Trans. Speech Audio Processing, vol. 11, no. 5, pp. 447-456, Sept. 2003.
5. Sh. Fine, J. Navratil, and R. A. Ganesh, "A hybrid GMM/SVM approach to speaker identification," in Proc. ICASSP'01, vol. 1, pp. 417-420, Salt Lake City, Utah, May 2001.
6. R. Saeidi, H. R. Sadegh Mohammadi, and M. Khalaj Amir-Hosseini, "An efficient GMM classification post-processing method for structural Gaussian mixture model based speaker verification," in Proc.ICASSP'06, vol. 1, pp. 909-912, , Toulouse, France, May 2006.
7. A. Chan, R. Mosur, A. Rudnicky, and J. Sherwani, "Four-layer categorization scheme of fast GMM computation techniques in large vocabulary continuous speech recognition systems," in Proc. INTERSPEECH'2004, pp. 689-692, 2004.
8. R. Saeidi, H. R. Sadegh Mohammadi, R. D. Rodman, and T. Kinnunen, "A new segmentation algorithm combined with transient frames power for text independent speaker verification," submitted to ICASSP'07.
9. H. R. Sadegh Mohammadi and R. Saeidi, "Efficient implementation of GMM based speaker verification using sorted Gaussian mixture model," in Proc. EUSIPCO '06, Florence, Italy, Sept. 4-8, 2006.
10. The 2000 NIST Speaker Recognition Evaluation, http://www.nist.gov/ speech/tests/spk/2000/index.htm