Advertisement

Experiments with Segmentation in an Online Speaker Diarization System

  • Marie KunešováEmail author
  • Zbyněk Zajíc
  • Vlasta Radová
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10415)

Abstract

In offline speaker diarization systems, particularly those aimed at telephone speech, the accuracy of the initial segmentation of a conversation is often a secondary concern. Imprecise segment boundaries are typically corrected during resegmentation, which is performed as the final step of the diarization process. However, such resegmentation is generally not possible in online systems, where past decisions are usually unchangeable. In such situations, correct segmentation becomes critical. In this paper, we evaluate several different segmentation approaches in the context of online diarization by comparing the overall performance of an i-vector-based diarization system set to operate in a sequential manner.

Keywords

Speaker diarization Speaker change detection i-vectors Convolutional neural network 

Notes

Acknowledgments

This research was supported by the Ministry of Culture of the Czech Republic, project No. DG16P02B009.

References

  1. 1.
    Bozonnet, S., Evans, N.W., Fredouille, C.: The LIA-EURECOM RT 2009 speaker diarization system: enhancements in speaker modelling and cluster purification. In: Proceedings ICASSP, pp. 4958–4961. IEEE (2010)Google Scholar
  2. 2.
    Canavan, A., Graff, D., Zipperlen, G.: CALLHOME American English speech, LDC97S42. In: LDC Catalog, Linguistic Data Consortium, Philadelphia (1997)Google Scholar
  3. 3.
    Church, K., Zhu, W., Vopicka, J., Pelecanos, J., Dimitriadis, D., Fousek, P.: Speaker diarization: a perspective on challenges and opportunities from theory to practice. In: Proceedings ICASSP, pp. 4950–4954 (2017)Google Scholar
  4. 4.
    Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788–798 (2011)CrossRefGoogle Scholar
  5. 5.
    Fergani, B., Davy, M., Houacine, A.: Speaker diarization using one-class support vector machines. Speech Commun. 50(5), 355–365 (2008)CrossRefGoogle Scholar
  6. 6.
    Garcia-Romero, D., Snyder, D., Sell, G., Povey, D., McCree, A.: Speaker diarization using deep neural network embedings. In: Proceedings ICASSP, pp. 4930–4934 (2017)Google Scholar
  7. 7.
    Gupta, V.: Speaker change point detection using deep neural nets. In: Proceedings ICASSP, pp. 4420–4424 (2015)Google Scholar
  8. 8.
    Hrúz, M., Zajíc, Z.: Convolutional neural network for speaker change detection in telephone speaker diarization system. In: Proceedings ICASSP, pp. 4945–4949 (2017)Google Scholar
  9. 9.
    Lapidot, I., Bonastre, J.F.: On the importance of efficient transition modeling for speaker diarization. In: Proceedings Interspeech, 08–12 September 2016, pp. 2190–2193 (2016)Google Scholar
  10. 10.
    NIST: The 2009 (RT-09) rich transcription meeting recognition evaluation plan (2009). http://www.itl.nist.gov/iad/mig/tests/rt/2009/docs/rt09-meeting-eval-plan-v2.pdf
  11. 11.
    Rouvier, M., Dupuy, G., Gay, P., Khoury, E., Merlin, T., Meignier, S.: An open-source state-of-the-art toolbox for broadcast news diarization. In: Proceedings Interspeech, pp. 1477–1481 (2013)Google Scholar
  12. 12.
    Sell, G., Garcia-Romero, D.: Speaker diarization with PLDA i-vector scoring and unsupervised calibration. In: IEEE Spoken Language Technology Workshop, pp. 413–417 (2014)Google Scholar
  13. 13.
    Senoussaoui, M., Kenny, P., Stafylakis, T., Dumouchel, P.: A study of the cosine distance-based mean shift for telephone speech diarization. IEEE/ACM Trans. Audio Speech Lang. Process. 22(1), 217–227 (2014)CrossRefGoogle Scholar
  14. 14.
    Shum, S., Dehak, N., Chuangsuwanich, E., Reynolds, D., Glass, J.: Exploiting intra-conversation variability for speaker diarization. In: Proceedings Interspeech, pp. 945–948 (2011)Google Scholar
  15. 15.
    Wang, R., Gu, M., Li, L., Xu, M., Zheng, T.F.: Speaker segmentation using deep speaker vectors for fast speaker change scenarios. In: Proceedings ICASSP, pp. 5420–5424 (2017)Google Scholar
  16. 16.
    Zajíc, Z., Kunešová, M., Radová, V.: Investigation of segmentation in i-vector based speaker diarization of telephone speech. In: Ronzhin, A., Potapova, R., Németh, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 411–418. Springer, Cham (2016). doi: 10.1007/978-3-319-43958-7_49 CrossRefGoogle Scholar
  17. 17.
    Zajíc, Z., Machlica, L., Müller, L.: Initialization of fMLLR with sufficient statistics from similar speakers. In: Habernal, I., Matoušek, V. (eds.) TSD 2011. LNCS (LNAI), vol. 6836, pp. 187–194. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23538-2_24 CrossRefGoogle Scholar
  18. 18.
    Zajíc, Z., Hrúz, M., Müller, L.: Speaker diarization using convolutional neural network for statistics accumulation refinement. In: Proceedings Interspeech (2017, in press)Google Scholar
  19. 19.
    Zhu, W., Pelecanos, J.: Online speaker diarization using adapted i-vector transforms. In: Proceedings ICASSP, pp. 5045–5049. IEEE (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Marie Kunešová
    • 1
    • 2
    Email author
  • Zbyněk Zajíc
    • 1
  • Vlasta Radová
    • 1
    • 2
  1. 1.NTIS - New Technologies for the Information Society, Faculty of Applied SciencesUniversity of West BohemiaPlzeňCzech Republic
  2. 2.Department of Cybernetics, Faculty of Applied SciencesUniversity of West BohemiaPlzeňCzech Republic

Personalised recommendations