Skip to main content
SpringerLink
Log in

A novel hybrid feature method based on Caelen auditory model and gammatone filterbank for robust speaker recognition under noisy environment and speech coding distortion

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Currently, the majority of the state-of-the-art speaker recognition systems predominantly use short-term cepstral feature extraction approaches to parameterize the speech signals. In this paper, we propose new auditory features based Caelen auditory model that simulate the external, middle and inner parts of the ear and Gammtone filter for speaker recognition system, called Caelen Auditory Model Gammatone Cepstral Coefficients (CAMGTCC). The performances evaluations of the proposed feature are carried by the TIMIT and NIST 2008 corpus. The speech coding represent by Adaptive Multi-Rate wideband (AMR-WB) and noisy conditions using various noises SNR levels which are extracted from NOISEX-92. Speaker recognition system using GMM-UBM and i-vector-GPLDA modelling. The experimental results demonstrate that the proposed feature extraction method performs better compared to the Gammatone Cepstral Coefficients (GTCC) and Mel Frequency Cepstral Coefficients (MFCC) features. For speech coding distortion, the features extraction proposed improve the robustness of codec-degraded speech at different bit rates. In addition, when the test speech signals are corrupted with noise at SNRs ranging from (0 dB to 15 dB), we observe that CAMGTCC achieves overall equal error rate (EER) reduction of 10.88% to 6.8% relative, compared to baselines.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Al-Ali AKH, Dean D, Senadji B, Chandran V, Naik GR (2017) Enhanced forensic speaker verification using a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions. IEEE Access 5(15400–15):413–15413

    Google Scholar 

  2. Bellot O, Matrouf D, Merlin T, Bonastre JF (2000) Additive and convolutional noises compensation for speaker recognition In Sixth International Conference on Spoken Language Processing

  3. Caelen J (1985) Space/Time data-information in the ARIAL project ear model. Speech Commun 4(1)

  4. Chandra, M., Nandi, P., & Mishra, S. (2015). Spectral-subtraction based features for speaker identification. In proceedings of the 3rd international conference on Frontiers of intelligent computing: theory and applications (FICTA) 2014 (pp. 529–536). Springer, Cham

  5. Chaouch H, Merazka F, Marthon P (2019) Multiple description coding technique to improve the robustness of ACELP based coders AMR-WB. Speech Commun 108:33–40

    Article  Google Scholar 

  6. Chu W (2003) Speech coding algorithms: Foundation and Evolution of Standardized Coders A. John Wiley & Sons

    Book  MATH  Google Scholar 

  7. Dunn RB, Quatieri TF, Reynolds DA, Campbell JP (2001). Speaker recognition from coded speech and the efects of score normalization. In proceedings of conference record of ThirtyFifth Asilomar conference on signals, systems and computers (Vol. 2, pp. 1562–1567)

  8. Fedila M, Amrouche A (2012) Automatic speaker recognition for mobile communications using AMR- WB speech coding. IEEE, information science, signal processing and their applications , ISSPA, pp. 1034–1038.

  9. Fedila M, Bengherabi M, Amrouche A (2017) Gammatone filterbank and symbiotic combination of amplitude and phase-based spectra for robust speaker verification under noisy conditions and compression artifacts. Multimedia Tools Appl:1–19.

  10. Gallardo LF (2016) Human and automatic speaker recognition over telecommunication channels. Springer Science + Business Media, Singapore

  11. Ghitza O (1994) Auditory models and human performance in tasks related to speech coding and speech recognition. IEEE Trans. Speech AudioProcess. 2:115–132

    Article  Google Scholar 

  12. Glasberg M (1990) Derivation of auditory filter shapes from notched-noise data. Journal of Hering Elsevier 47(1–2):103–138

    Google Scholar 

  13. Grassi S, Besacier L, Dufaux A, Ansorge M, and Pellandini F (2000) Influence of GSM speech coding on the performance of textindependent speaker recognition,” in Proceedings of EUSIPCO pp. 437–440

  14. Hansen JHL, Hasan T (2015) Speaker recognition by machines and humans: a tutorial review. IEEE Signal Process Mag 32(6):74–99. https://doi.org/10.1109/MSP.2015.2462851

    Article  Google Scholar 

  15. Johannesma PIM (1972) The pre-response stimulus ensemble of neurons in the cochlear nucleus. In:Symposium on hearing theory (IPO, Eindhoven, The Netherlands), pp. 58–69

  16. Kadi KL, Selouani SA, Boudraa B, Boudraa M (2016) Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge. Biocybernetics Biomed Eng 36(1):233–247

    Article  Google Scholar 

  17. Kinnunen T, Alam MJ, Matejka P, Kenny P, Cernocky J, OShaughnessy D (2013) Frequency warping and robust speaker verification: a comparison of alternative mel-scale representations. In: Proc. INTERSPEECH. Lyon, France, pp. 3122–3126

  18. Kinnunen T, Li H (2010) An overview of text-independent speaker recognition: from features to supervectors. Speech Commun 52:12–40

    Article  Google Scholar 

  19. Krobba A, Debyeche M, Amrouche A (2010) Evaluation of speaker identifcation system using GSM-EFR speech data. In proceedings of international conference on design and Technology of Integrated Systems (nanoscale era Hammamet) (pp. 1–5).

  20. Krobba A, Debyeche M, Selouani SA (2019) Maximum entropy PLDA for robust speaker recognition under speech coding distortion. Int J Speech Technol 22(4):1115–1122

    Article  Google Scholar 

  21. Krobba A, Debyeche M, Selouani SA (2019) Multitaper chirp group delay Hilbert envelope coefficients for robust speaker verification. Multimedia Tools Appl:1–18.

  22. Li Z, Gao Y (2016) Acoustic feature extraction method for robust speaker identification. Multimed Tools Appl 75(12):7391–7406

    Article  Google Scholar 

  23. Li Q, Huang Y (2011) An auditory-based feature extraction algorithm for robust speaker identification under mismatched conditions. IEEE Trans Audio Speech Lang Process 19(6):1791–1801

    Article  Google Scholar 

  24. Linguistic Data Consortium (1990) The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus. NIST Speech Disc:CD1–1.1

  25. Lyon RF, 1982. A computational model of filtering, detection, and compression in the cochlea. In: IEEE International Conference on Acoustics,Speech, and Signal Processing, pp. 1282–1285

  26. McCree A (2006). Reducing speech coding distortion for speaker identifcation. In Annual Conference (Interspeech) (pp. 941–944)

  27. Mclaren M, Abrash V, Graciarena M, Lei Y, Pesan J (2013) Improving robustness to compressed speech in speaker recognition. Interspeech, In, pp 3698–3702

  28. Ming J, Hazen TJ, Glass JR, Reynolds DA (2007) Robust speaker recognition in noisy conditions. IEEE Trans Audio Speech Lang Process 15(5):1711–1723

    Article  Google Scholar 

  29. NIST Year (2008) Speaker recognition evaluation plan, Technical report, NIST. http:www.itl.nist.gov/iad/mig/yest/ser/2008

  30. Peinado A, Segura J (2006) Speech recognition over digital channels: robustness and standards. isbn:978-0-470-02400-3

  31. Pohjalainen J, Hanilçi C, Kinnunen T, Alku P (2014) Mixture linear prediction in speaker verification under vocal effort mismatch. IEEE Signal Processing Letters 21(12):1516–1520

    Article  Google Scholar 

  32. Rahman MH, Kanagasundaram A, Himawan I, Dean D, Sridharan S (2018) Improving PLDA speaker verification performance using domain mismatch compensation techniques. Comp Speech Lang 47:240–258

    Article  Google Scholar 

  33. Recommendation G (2003) 722.2:Wideband Coding of Speech at around 16 kbit/s using Adaptive Multi-Rate Wideband (AMR-WB).

  34. Reynolds DA (2002) An overview of automatic speaker recognition technology. In IEEE international conference on acoustics, speech, and signal processing (Vol. 4, pp. IV-4072)

  35. Saeidi R, Pohjalainen J, Kinnunen T, Alku P (2010) Temporally weighted linear prediction features for tackling additive noise in speaker verification. IEEE Signal Processing Letters 17(6):599–602

    Article  Google Scholar 

  36. Samia AE, Nassar MA, Dessouky MI, Nabil A, Adel I, El-Fishawy S, El-Samie FEA. Text-independent speaker recognition using LSTM-RNN and speech enhancement. Multimedia Tools and Applications, 1–16

  37. Selouani SA (2011) Speech Processing and Soft Computing. Springer, New York

    Book  MATH  Google Scholar 

  38. Selouani SA, O’Shaughnessy D, Caelen J (2007) Incorporating phonetic knowledge into an evolutionary subspace approach for robust speechrecognition. Int. J. Comput. Appl. 29:143–154

    Google Scholar 

  39. Selouani SA, Alotaibi Y, Cichocki W, Gharsellaoui S, Kadi K (2015) Native and non-native class discrimination using speech rhythm-and auditory-based cues. Comp Speech Lang 31(1):28–48

    Article  Google Scholar 

  40. Seneff S (1988) A joint synchrony/mean-rate model of auditory speech processing. J. Phon. 16:55–76

    Article  Google Scholar 

  41. Seyed OS, Malcolm S, Heck L (2013) MSR identity toolbox v.1.0.A MATLAB toolbox for speaker recognition research In: Proc, IEEE Signal Process, Speech and Language Processing Technical Committee Newsletter

  42. Shabtai NR, Rafaely B, Zigel Y (2011) The effect of reverberation on the performance of cepstral mean subtraction in speaker verification. Appl Acoust 72(2–3):124–126

    Article  Google Scholar 

  43. Sreenivasa RK, Vuppala AK (2014) Speech processing in mobile environments. Springer, ISBN: 978– 319–03116-3.

  44. Tan ZH, Lindberg B (2008) Automatic speech recognition on mobile devices and over communication networks. Springer Science & Business Media

    Book  MATH  Google Scholar 

  45. Tan Z, Mak MW, Mak BKW, Zhu Y (2018) Denoised senone i-vectors for robust speaker verification. IEEE/ACM Trans Audio, Speech, Language Process 26(4):820–830

    Article  Google Scholar 

  46. Valero X, Alias F (2012) Gammatone cepstral coefficients: Biologically inspired features for non- speech audio classification. IEEE Transactions on Multimedia 14(6):1684–1689

    Article  Google Scholar 

  47. Varga A, Steeneken HJ (1993) Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun 12(3):247–251 http://spib.rice.edu/spib/selectnoise.html

  48. Vuppala AK, Rao KS, Chakrabarti S (2013) Improved speaker identifcation in wireless environment. Int J Signal Imaging Syst Eng 6(3):130–137

    Article  Google Scholar 

  49. Yu D, Deng L, Droppo J, Wu J, Gong Y, Acero A (2008) A minimum-mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition. In 2008 IEEE international conference on acoustics, speech and signal processing (pp. 4041-4044). IEEE

  50. Zhao X, Shao Y, Wang DL (2012) CASA-based robust speaker identification. IEEE Trans Audio, Speech, Lang Process 20(5):1608–1161

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Speech Communication and Signal Processing Laboratory, Faculty of Electrical engineering, University of USTHB, Algiers, Algeria

    Ahmed Krobba & Mohamed Debyeche

  2. LARIHS Laboratory, Campus Shappaing, University of Moncton, Moncton, Canada

    Sid. Ahmed Selouani

Authors
  1. Ahmed Krobba
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohamed Debyeche
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sid. Ahmed Selouani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ahmed Krobba.

Ethics declarations

Conflict of interest

The Authors declare no conflicts of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Krobba, A., Debyeche, M. & Selouani, S.A. A novel hybrid feature method based on Caelen auditory model and gammatone filterbank for robust speaker recognition under noisy environment and speech coding distortion. Multimed Tools Appl 82, 16195–16212 (2023). https://doi.org/10.1007/s11042-022-14068-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-14068-4

Keywords

Search

Navigation