Skip to main content
SpringerLink
Log in

Speaker Verification Method Based on Two-Layer GMM-UBM Model in the Complex Environment

  • Conference paper
  • First Online:
Brain Informatics (BI 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10654))

Included in the following conference series:

Abstract

In order to improve speaker verification accuracy in the complex environment, a two-layer Gaussian mixture model-universal background model (GMM-UBM) model based on speaker verification method is proposed. For different layer, a GMM-UBM model was trained by different combination of speech features. The voice data of 3 days (36 h) were recorded from the complex environment, and the collected data was manually segmented into four classes: quiet, noise, target speaker and other speaker. Not only the segment data can be used to train GMM-UBM model, but also it can provide a criterion to assess the effectiveness of the model. The results show that the highest recall for the second and third day were 0.75 and 0.74 respectively, and the corresponding specificity were 0.29 and 0.19, which indicates the proposed GMM-UBM model is viable to verify the target speaker in the complex environment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chen, J., Zhong, N.: Data-brain modeling for systematic brain informatics. In: Brain Informatics, International Conference, BI, Beijing, China, October 22–24 (2009)

    Google Scholar 

  2. Zhong, N., Motomura, S.: Agent-enriched data mining: a case study in brain informatics. IEEE Intell. Syst. 24, 38–45 (2009)

    Article  Google Scholar 

  3. Li, N., Mak, M.W.: SNR-invariant PLDA modeling in nonparametric subspace for robust speaker verification. IEEE/ACM Trans. Audio Speech/Language Process. 23, 1648–1659 (2015)

    Article  Google Scholar 

  4. Ding, I.J., Yen, C.T., Ou, D.C.: A method to integrate GMM, SVM and DTW for speaker recognition. Int. J. Eng. Technol. Innov. 4, 38–47 (2014)

    Google Scholar 

  5. Wu, H., Wang, Y., Huang, J.: Blind detection of electronic disguised voice. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3013–3017 (2013)

    Google Scholar 

  6. Wang, X., Yang, T., Yu, Y., Zhang, R., Guo, F.: Footstep-identification system based on walking interval. Intell. Syst. IEEE 30, 46–52 (2015)

    Article  Google Scholar 

  7. Turner, C., Joseph, A.: A wavelet packet and mel-frequency cepstral coefficients-based feature extraction method for speaker identification. Procedia Comput. Sci. 61, 416–421 (2015)

    Article  Google Scholar 

  8. Haris, B.C., Sinha, R.: Low-Complexity Speaker Verification with Decimated Supervector Representations. Elsevier Science Publishers B. V., Amsterdam (2015)

    Google Scholar 

  9. Wang, Y., Wu, H., Huang, J.: Verification of Hidden Speaker Behind Transformation Disguised Voices. Academic Press, Inc, Orlando (2015)

    Google Scholar 

  10. Kanagasundaram, A., Dean, D., Sridharan, S.: Improving PLDA speaker verification with limited development data. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1665–1669 (2014)

    Google Scholar 

  11. Rajan, P., Afanasyev, A., Hautamki, V., Kinnunen, T.: From single to multiple enrollment i-vectors: practical PLDA scoring variants for speaker verification. Digit. Signal Proc. 31, 93–101 (2014)

    Article  Google Scholar 

  12. Xu, L., Yang, Z.: Speaker identification based on state space model. Int. J. Speech Technol. 19, 1–8 (2016)

    Article  Google Scholar 

  13. Rakhmanenko, I., Meshcheryakov, R.: Speech Features Evaluation for Small Set Automatic Speaker Verification Using GMM-UBM System (2016)

    Google Scholar 

  14. Sarkar, A.K., Tan, Z.H.: Text Dependent Speaker Verification Using un-supervised HMM-UBM and Temporal GMM-UBM. In: Interspeech (2016)

    Google Scholar 

  15. Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Language Process. 19, 788–798 (2011)

    Article  Google Scholar 

  16. Jagtap, S.S., Bhalke, D.G.: Speaker verification using Gaussian mixture model. In: International Conference on Pervasive Computing, pp. 1–5 (2015)

    Google Scholar 

Download references

Acknowledgments

This work is partially supported by the National Basic Research Program of China (No. 2014CB744600), National Natural Science Foundation of China (No. 61420106005), Beijing Natural Science Foundation (No. 4164080), and Beijing Outstanding Talent Training Foundation (No. 2014000020124G039).

Author information

Authors and Affiliations

  1. International WIC Institute, Beijing University of Technology, Beijing, 100024, China

    Qiang He, Haiyan Zhou & Ning Zhong

  2. Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China

    Qiang He, Haiyan Zhou & Ning Zhong

  3. Beijing Key Laboratory of MRI and Brain Informatics, Beijing, China

    Qiang He, Haiyan Zhou & Ning Zhong

  4. Beijing Anding Hospital of Capital Medical University, Beijing, China

    Jie Yang

  5. Department of Life Science and Informatics, Maebashi Institute of Technology, Maebashi-City, 371-0816, Japan

    Zhijiang Wan & Ning Zhong

Authors
  1. Qiang He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhijiang Wan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haiyan Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ning Zhong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ning Zhong .

Editor information

Editors and Affiliations

  1. Chinese Academy of Sciences, Beijing, China

    Yi Zeng

  2. Beijing Normal University, Beijing, China

    Yong He

  3. KTH Royal Institute of Technology and Karolinska Institute, Stockholm, Sweden

    Jeanette Hellgren Kotaleski

  4. University of California, San Diego, San Diego, California, USA

    Maryann Martone

  5. Chinese Academy of Sciences, Beijing, China

    Bo Xu

  6. Allen Institute for Brain Science, Seattle, Washington, USA

    Hanchuan Peng

  7. Wuhan National Lab Optoelectronics, Huazhong University of Science and Technology, Wuhan, China

    Qingming Luo

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

He, Q., Wan, Z., Zhou, H., Yang, J., Zhong, N. (2017). Speaker Verification Method Based on Two-Layer GMM-UBM Model in the Complex Environment. In: Zeng, Y., et al. Brain Informatics. BI 2017. Lecture Notes in Computer Science(), vol 10654. Springer, Cham. https://doi.org/10.1007/978-3-319-70772-3_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-70772-3_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-70771-6

  • Online ISBN: 978-3-319-70772-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation