Skip to main content
SpringerLink
Log in

Using DTW neural–based MFCC warping to improve emotional speech recognition

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In recognition of emotional speech, the performance of automatic speech recognition (ASR) systems is degraded significantly. To improve the recognition rate of ASR systems, we can neutralize the Mel-frequency cepstral coefficients (MFCCs) of emotional speech as the most frequently used features in ASR. In this way, the neutralized MFCCs are used in a hidden Markov model (HMM)-based ASR system that has been trained by nonemotional speech. In this paper, the frequency range that is most affected by emotion is determined, and the frequency warping is applied in the calculation process of MFCCs. This warping is performed in Mel filterbank module and/or discrete cosine transform (DCT) module in the process of MFCCs’ calculation. To determine the warping factor, a combined structure using dynamic time warping (DTW) technique and multi-layer perceptron (MLP) neural network is used. Experimental results show that the recognition rate in anger and happiness emotional states is improved when the warping is performed in each of the mentioned modules when the MFCCs are calculated. Also, when the warping is performed in both the Mel filterbank and the DCT modules, the recognition rate of speech in anger and happiness emotional states is improved by 6.4 and 3.0%, respectively.

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

Similar content being viewed by others

References

  1. Strik H, Cucchiarini C (1999) Modeling pronunciation variation for ASR: a survey of the literature. Speech Commun 29:225–246

    Article  Google Scholar 

  2. Vlasenko B, Wendemuth A (2009) Heading toward to the natural way of human-machine interaction: the NIMITEK project. Proceedings of IEEE international conference on multimedia and expo, pp 950–953

  3. Ijima Y, Tachibana M, Nose T, Kobayashi T (2009) Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM. Proceedings of IEEE international conference on acoustic, speech and signal processing, pp 4157–4160

  4. Ververidis D, Kotropoulos C (2006) Emotional speech recognition: resources, features, and methods. Speech Commun 48:1162–1181

    Article  Google Scholar 

  5. Schuller B, Seppi D, Batliner A, Maier A, Steidl S (2007) Towards more reality in the recognition of emotional speech. Proceedings of IEEE international conference on acoustic, speech and signal processing, vol 4, pp 941–944

  6. Schuller B, Batliner A, Steidl S, Seppi D (2009) Emotion recognition from speech: putting ASR in the loop. Proceedings of IEEE international conference on acoustic, speech and signal processing, pp 4585–4588

  7. Krajewski J, Batliner A, Kessel S (2010) Comparing multiple classifiers for speech-based detection of self-confidence-A pilot study. Proceedings international conference on pattern recognition, pp 3716–3719

  8. Athanaselis T, Bakamidis S, Dologlou I, Cowie R, Douglas-Cowie E, Cox C (2005) ASR for emotional speech: clarifying the issues and enhancing performance. J Neural Netw 18:437–444

    Article  Google Scholar 

  9. Litman DJ, Hirschberg JB, Swerts M (2000) Predicting automatic speech recognition performance using prosodic cues. Proceedings North American chapter of the association for computational linguistics conference, pp 218–225

  10. Steeneken HJM, Hansen JHL (1999) Speech under stress conditions: overview of the effect of speech production and on system performance. Proceedings of IEEE international conference on acoustic, speech and signal processing, vol 4, pp 2079–2082

  11. Benzeghiba M, De Mori R, Deroo O, Dupont S, Erbes T, Jouvet D, Fissore L, Laface P, Mertins A, Ris C, Rose R, Tyagi V, Wellekens C (2007) Automatic speech recognition and speech variability: a review. Speech Commun 49:763–786

    Article  Google Scholar 

  12. Hansen JH, Patil S (2007) Speech under stress: analysis, modeling and recognition. Springer, Berlin, pp 108–137

    Google Scholar 

  13. Gharavian D (2004) Prosody in Farsi language and its use in recognition of intonation and speech. Ph.D. Dissertation, Electrical Engineering Department, Amirkabir University of Technology, Tehran

  14. Gharavian D, Ahadi SM (2006) Recognition of emotional speech and speech emotion in Farsi. Proceedings of international symposium on Chinese spoken language processing, vol 2, pp 299–308

  15. Gharavian D, Ahadi SM (2005) The effect of emotion on Farsi speech parameters: a statistical evaluation. Proceedings of international conference on speech and computer, pp 463–466

  16. Gharavian D, Sheikhan M, Janipour M (2010) Pitch in emotional speech and emotional speech recognition using pitch frequency. Majlesi J Electr Eng 4(1):19–24

    Google Scholar 

  17. Bosch LT (2003) Emotions, speech and the ASR framework. Speech Commun 40:213–225

    Article  MATH  Google Scholar 

  18. Müller F, Mertins A (2011) Contextual invariant-integration features for improved speaker-independent speech recognition. Speech Commun. doi:10.1016/j.specom.2011.02.002 Article in Press

  19. Welling L, Ney H, Kanthak S (2002) Speaker adaptive modeling by vocal tract normalization. IEEE Trans Speech Audio Process 10:415–426

    Article  Google Scholar 

  20. Sinha R, Umesh S (2002) Non-uniform scaling based speaker normalization. Proceedings of IEEE international conference on acoustic, speech and signal processing, vol 1, pp 589–592

  21. Gales MJF (1998) Maximum likelihood linear transformations for HMM-based speech recognition. Comput Speech Lang 12:75–98

    Article  Google Scholar 

  22. Byrne W, Doermann D, Franz M, Gustman S, Hajič J, Oard D, Picheny M, Psutka J, Ramabhadran B, Soergel D, Ward T, Zhu W-J (2004) Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans Speech Audio Process 12:420–435

    Article  Google Scholar 

  23. Godfrey J, Holliman E, McDaniel J (1992) SWITCHBOARD: telephone speech corpus for research and development. Proceedings of IEEE international conference on acoustic, speech and signal processing, pp 517–520

  24. Pan YC, Xu MX, Liu LQ, Jia PF (2006) Emotion-detecting based model selection for emotional speech recognition. Proceedings of multiconference on computational engineering in system applications, pp 2169–2172

  25. Meng H, Pittermann J, Pittermann A, Minker W (2007) Combined speech-emotion recognition for spoken human-computer interfaces. Proceedings IEEE international conference on signal processing and communications, pp 1179–1182

  26. Sun Y, Zhou Y, Zhao Q, Yan Y (2009) Acoustic feature optimization for emotion affected speech recognition. Proceedings of international conference on information engineering and computer science, pp 1–4. doi:10.1109/ICIECS.2009.5365821

  27. Muralishankar R, Sangwan A, O’Shaughnessy D (2007) Theoretical complex cepstrum of DCT and warped DCT filters. IEEE Signal Process Lett 14:367–370

    Article  Google Scholar 

  28. Chang J-H (2005) Warped discrete cosine transform-based noisy speech enhancement. IEEE Trans Circuits Syst II 52:535–539

    Article  Google Scholar 

  29. Panchapagesan S (2006) Frequency warping by linear transformation of standard MFCC. Proceedings of interspeech, pp 397–400

  30. Pitz M, Molau S, Schlueter R, Ney H (2001) Vocal tract normalization equals linear transformation in cepstral space. Proceedings of European conference on speech communication and technology, pp 721–724

  31. Clavel C, Vasilescu I, Devillers L (2011) Fiction support for realistic portrayals of fear-type emotional manifestations. Comput Speech Lang 25:63–83

    Article  Google Scholar 

  32. Bijankhan M, Sheikhzadegan J, Roohani MR, Samareh Y, Lucas C, Tebiani M (1994) The speech database of Farsi spoken language. Proceedings of Australian international conference on speech science and technology, pp 826–831

  33. Young SJ, Evermann G, Kershaw D, Moore G, Odell J, Ollason D, Povey D, Valtchev V, Woodland V (2002) The HTK book (Ver.3.2). Cambridge University, Cambridge

  34. McCandless SS (1974) An Algorithm for formant extraction using linear prediction spectra. IEEE Trans Acoustics Speech Signal Process 22:135–141

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electrical Engineering Department, Islamic Azad University, South Tehran Branch, Tehran, Iran

    Mansour Sheikhan & Farhad Ashoftedel

  2. Electrical Engineering Department, Shahid Abbaspour University, Tehran, Iran

    Davood Gharavian

Authors
  1. Mansour Sheikhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Davood Gharavian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Farhad Ashoftedel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mansour Sheikhan.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sheikhan, M., Gharavian, D. & Ashoftedel, F. Using DTW neural–based MFCC warping to improve emotional speech recognition. Neural Comput & Applic 21, 1765–1773 (2012). https://doi.org/10.1007/s00521-011-0620-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0620-8

Keywords

Search

Navigation