Computationally efficient and robust BIC-based speaker segmentation

IEEE Transactions on Audio, Speech and Language Processing

Volumn 16, Issue 5, 2008, Pages 920-933

  Kotti, Margarita ^a   Benetos, Emmanouil ^a   Kotropoulos, Constantine ^a  

^a ARISTOTLE UNIVERSITY OF THESSALONIKI   (Greece)

Author keywords

Automatic speaker segmentation; Bayesian infor mation criterion (BIC); Inverse Gaussian distribution; Simultaneous diagonalization; Speaker utterance duration distribution; Speech analysis

Indexed keywords

AUTOMATIC SPEAKER SEGMENTATION; BAYESIAN INFOR-MATION CRITERION (BIC); INVERSE GAUSSIAN DISTRIBUTION; SIMULTANEOUS DIAGONALIZATION; SPEAKER UTTERANCE DURATION DISTRIBUTION;

BAYESIAN NETWORKS; COVARIANCE MATRIX; GAUSSIAN DISTRIBUTION; LINEAR PROGRAMMING; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH ANALYSIS;

COMPUTATIONAL EFFICIENCY;

EID: 66149116378     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2008.925152     Document Type: Article

References (45)

1. H. G. Kim and T. Sikora, "Comparison of MPEG-7 audio spectrum projection features and MFCC applied to speaker recognition, sound classification and audio segmentation," in Proc. 2004 IEEE Int. Conf. Acoust., Speech, Signal Process., Montreal, QC, Canada, May 2004, vol. 5, pp. 925-928.
2. "The Segmentation Task: Find the Story Boundaries." [Online]. Available: http://www.nist.gov/speech/tests/tdt/tdt99/presenta-tions/NIST- segmentation/index.htm
3. "NIST Rich Transcription Evaluation," [Online]. Available:http://www.nist.gov/speech/tests/rt/
4. T. Wu, L. Lu, K. Chen, and H. Zhang, "UBM-based real-time speaker segmentation for broadcasting news," in Proc. 2003 IEEE Int. Conf. Acoust., Speech, Signal Process., Hong Kong, Apr. 2003, vol. 2, pp. 193-196.
5. S. Know and S. Narayanan, "Unsupervised speaker indexing using generic models," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 1004-1013, Sep. 2005.
6. M. Collet, D. Charlet, and F. Bimbot, "A correlation metric for speaker tracking using anchor models," in Proc. 2005 IEEE Int. Conf. Acoust., Speech, Signal Process., Philadelphia, PA, Mar. 2005, vol. 1, pp. 713-716. (Pubitemid 43761252)
7. A. Tritschler and R. Gopinath, "Improved speaker segmentation and segments clustering using the Bayesian information criterion," in Proc. 6th Eur. Conf. Speech Commun. Techoi, Budapest, Hungary, Sep. 1999, pp. 679-682.
8. H. Kim, D. filter, and T. Sikora, "Hybrid speaker-based segmentation system using model-level clustering," in Proc. 2005 IEEE Int. Conf. Acoust., Speech, Signal Process., Philadelphia, PA, Mar. 2005, vol. I, pp. 745-748. (Pubitemid 43761260)
9. S. Meignier, D. Moraru, C. Fredouille, J. F. Bonastre, and L. Besacier, "Step-by-step and integrated approaches in broadcast news speaker diarization," Compul. Speech Lang., vol. 20, no. 2-3, pp. 303-330, Apr.-Jul. 2006.
10. J. A. Arias, J. Pinquier, and R. Andre-Obrecht, "Evaluation of classification techniques for audio indexing," in Proc. 13th Eur. Signal Process. Conf., Antalya, Turkey, Sep. 2005, CD-ROM.
11. S. Know and S. Narayanan, "Speaker change detection using a new weighted distance measure," in Proc. Int. Conf. Spoken Lang., Sep. 2002, vol. 4, pp. 2537-2540.
12. P. Delacourt and C. J. Wellekens, "DISTBIC: A speaker-based segmentation for audio data indexing," Speech Commun., vol. 32, pp. 111-126, Sep. 2000.
13. L. Lu and H. Zhang, "Unsupervised speaker segmentation and tracking in real-time audio content analysis," Multimedia Syst., vol. 10, no. 4, pp. 332-343, Apr. 2005.
14. H. Harb and L. Chen, "Audio-based description and structuring of videos," Int. J. Digital Libraries, vol. 6, no. 1, pp. 70-81, Feb. 2006.
15. B. Zhou and J. H. L. Hansen, "Efficient audio stream segmentation via the combined T2 statistic and the Bayesian information criterion," IEEE Trans. Audio, Speech, Lang. Process., vol. 13, no. 4, pp. 467-174, Jul. 2005.
16. J. H. L. Hansen, R. Huang, B. Zhou, M. Seadle, J. R. Deller, A. R. Gurijala, M. Kurimo, and P. Angkititrakul, "SpeechFind: Advances in spoken document retrieval for a national gallery of the spoken word," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 712-730, Sep. 2005.
17. M. Cettolo and M. Vescovi, "Efficient audio segmentation algorithms based on the BIC," in Proc. 2003 IEEE Int. Conf. Acoust., Speech, Signal Process., Hong Kong, Apr. 2003, vol. 6, pp. 537-540.
18. J. Ajmera, I. McCowan, and H. Bourlard, "Robust speaker change de-tection," IEEE Signal Process. Lett., vol. 11, no. 8, pp. 649-651, Aug. 2004.
19. D. A. Reynolds and P. Torres-Carrasquillo, "Approaches and applica-tions of audio diarization," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Philadelphia, PA, Mar. 2005, vol. 5, pp. 953-956.
20. C. H. Wu, Y. H. Chiu, C. J. Shia, and C. Y. Lin, "Automatic segmenta-tion and identification of mixed-language speech using delta-BIC and LSA-based GMMs," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 1, pp. 266-276, Jan. 2006.
21. M. Kotti, L. G. P. M. Martins, E. Benetos, J. S. Cardoso, and C. Kotropoulos, "Automatic speaker segmentation using multiple fea-tures and distance measures: A comparison of three approaches," in Proc. IEEE Int. Conf. Multimedia Expo, Toronto, ON, Canada, Jul. 2006, pp. 1101-1104. (Pubitemid 46679913)
22. C. H. Wu and C. H. Hsieh, "Multiple change-point audio segmentation and classification using an MDL-based Gaussian model," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 2, pp. 647-657, Mar. 2006. (Pubitemid 46405361)
23. S. Cheng and H. Wang, "Metric SEQDAC: A hybrid approach for audio segmentation," in Proc. 8th Int. Conf. Spoken Lang. Process., Jeju, Korea, Oct. 2004, pp. 1617-1620.
24. F. Van der Heijden, R. P. W. Duin, D. de Ridder, and D. M. J. Tax, Classification, Parameter Estimation and State Estimation: An Engi-neering Approach Using MATLAB. London, U.K.: Wiley, 2004.
25. N. A. Campbell, "Robust procedures in multivariate analysis I: Robust covariance estimation," Appl. Statist., vol. 29, no. 3, pp. 231-237,1980.
26. G. A. F. Seber, Multivariate Observations. New York: Wiley, 1994.
27. S. Tadjudin and D. A. Landgrebe, "Covariance estimation with limited training samples,," IEEE Trans. Geosci. Remote Sen., vol. 37, no. 4, pp. 2113-2118, Jul. 1999.
28. J. S. Garofolo, "DARPA TIMIT Acoustic-phonetic continuous speech corpus," in Linguistic Data Consortium, Philadelphia, PA, 1993.
29. R. D. Reiss and M. Thomas, Statistical Analysis of Extreme Values. Basel, Germany: Birkhauser Verlag, 1997.
30. M. Kotti, E. Benetos, C. Kotropoulos, and I. Pitas, "A neural network approach to audio-assisted movie dialogue detection," Neurocomput., Special Iss.: Adv. Neural Netw. for Speech Audio Process., vol. 71, no. 1-3, pp. 157-166, Dec. 2007. (Pubitemid 350028667)
31. J. L. Folks and R. S. Chhikara, "The inverse Gaussian distribution and its statistical application-A review," J. R. Statist. Soc. B, vol. 40, pp. 263-289, 1978.
32. N. L. Johnson, S. Kotz, and S. Balakrishnan, Continuous Univariate Distributions. , New York: Wiley, 1994, vol. 1.
33. S. I. Boyarchenko and S. Z. Levendorskii, "Perpetual American pro-cesses under Levi processes," SI AM J. Control Optim., vol. 40, no. 6, pp. 1514-1516, Jun. 2001.
34. M. C. K. Tweedie, "Statistical properties of inverse Gaussian distribu-tions I," Ann. Math. Statist., vol. 28, no. 2, pp. 362-377, Jun. 1957.
35. X. D. Huang, A. Acero, and H.-S. Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Upper River Saddle, NJ: Pearson Education-Prentice-Hall, 2001.
36. R. Kohavi and G. H. John, "Wrappers for feature subset selection," Artif. lntell, vol. 97, no. 1-2, pp. 273-324, Dec. 1997. (Pubitemid 127401107)
37. G. Almpanidis and C. Kotropoulos, "Phonemic segmentation using the generalised Gamma distribution and small sample Bayesian informa-tion criterion," Speech Commun., vol. 50, no. 1, pp. 38-55, Jan. 2008. (Pubitemid 47576260)
38. M. Kotti, V. Moschou, and C. Kotropoulos, "Speaker segmentation and clustering," Signal Process., vol. 88, no. 5, pp. 1091-1124, May 2008.
39. J. J. Barnette and J. E. McLean, "The Tukey honestly significant dif-ference procedure and its control of the type I error-rate," in Proc. Annu. Meeting Mid-South Edit. Res. Assoc, New Orleans, LA, 1998, CD-ROM.
40. C. Barras, X. Zhu, S. Meignier, and J. L. Gauvain, "Multistage speaker diarization of broadcast news," IEEE Trans. Audio Speech, Lang. Process., vol. 14, no. 5, pp. 1505-1512, Sep. 2006. (Pubitemid 46547577)
41. J. Fiscus, "1997 English broadcast news speech (HUB4)," Linguistic Data Consortium, Philadelphia, PA, 1998.
42. D. Graff, J. Fiscus, and J. Garofolo, "1997 HUB4 English evaluation speech and transcripts," Linguistic Data Consortium, Philadelphia, PA, 2002.
43. R. R. Korfhase, Information Storage and Retrieval. New York: Wiley, 1997.
44. S. Strassel, C. Walker, and H. Lee, "RT-03 MDE training data speech," Linguistic Data Consortium, Philadelphia, PA, 2004.
45. G.H. Golub and C. F. Van Loan, Matrix Computations, 3rd ed. Bal-timore, MD: Johns Hopkins Univ. Press, 1996.