UBM-based incremental speaker adaptation

Proceedings - IEEE International Conference on Multimedia and Expo

Volumn 2, Issue , 2003, Pages 721-724

  Wu, Ting Yao ^a   Lu, Lie ^b   Chen, Ke ^a   Zhang, Hong Jiang ^a  

^a Center for Life Sciences   (China)

^b PEKING UNIVERSITY   (China)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTATION ALGORITHMS; LIMITED TRAINING DATA; NOVEL ALGORITHM; REAL-TIME OPERATION; REALTIME PROCESSING; SPEAKER ADAPTATION; SPEAKER SEGMENTATIONS; UNIVERSAL BACKGROUND MODEL;

DIGITAL STORAGE;

EID: 61949211336     PISSN: 19457871     EISSN: 1945788X     Source Type: Conference Proceeding    
DOI: 10.1109/ICME.2003.1221718     Document Type: Conference Paper

References (7)

1. J. P. Campbell, JR. "Speaker Recognition: A Tutorial" , Proc. of the IEEE, vl. 85, No. 9 (1997). pp. 1437-1462.
2. S.-J. Doh, and R. M. Stern, " Inter-class MLLR for speaker adaptation", Proceeding of International Conference of Acoustics, Speech, and Signal Processing (2000), Vol. 3, pp. 1543-1546.
3. D. A. Reynolds, T. F. Quatieri and R. B. Dunn, " Speaker Verification Using Adapted Gaussian Mixture Models", Digital Signal Processing 10 (2000), pp. 19-4-1.
4. T. Y. Wu, L. Lu, K. Chen, H. J. Zhang, "UBM-Based rea-time speaker segmentation for broadcasting news ", submitted to International Conference on Acoustic, Speech and Signal Processing (2003)
5. L. Lu, H. J. Zhang, "Speaker Change Detection and tracking in Real-time News Broadcasting Analysis " Proc of ACM Multimedia (2002), pp. 602-610.
6. F. K. Soong, A. E. Rosenberg, L. R. Rabiner, and B. H. Zhuang, " A vector quantization approach to speaker identification", in Proceeding of International Conference of Acoustics, Speech, and S ignal Processing, Tampa (1985), FL, pp. 387-390.
7. D. A. Reynolds, Comparison of background normalization methods for text-independent speaker verification, In Pro-ceedings of the European Conference on Speech Communication and Technology (1997), pp. 963-966