Speech Intelligibility Based Enhancement System Using Modified Deep Neural Network and Adaptive Multi-band Spectral Subtraction

  • Tusar Kanti DashEmail author
  • Sandeep Singh Solanki


In contrast to the adverse environments, performances of existing speech enhancement algorithms do not always produce satisfactory results. In the case of worst signal to noise ratio, the processing is complicated and it may introduce signal distortions and degradation of intelligibility. To overcome the complexity of the existing speech enhancement algorithms, a hybrid concept for enhancing the speech quality and intelligibility is proposed in this research. The primary objectives of the research work is to increase the intelligibility of the speech enhancement system that has been trained for a particular speech signal using modified deep neural network (DNN) and adaptive multi-band spectral subtraction (AdMBSS). In this work, AdMBSS is used for enhancing the intelligibility of the speech signal using the additional phase information calculation, and finally, hybrid DNN and Nelder Mead optimization is utilized to improve the signal quality. Experimental results explain that the proposed framework achieves improved performance in signal to noise ratio, perceptual evaluation of signal quality and minimum mean square error. Finally, performances are taken for the more noises like bus noise, train noise, babble noise, airport noise, station noise and exhibition noise.


Speech enhancement Speech intelligibility Feature extraction Optimization 



  1. 1.
    Hu, Y., & Loizou, P. C. (2007). Subjective comparison and evaluation of speech enhancement algorithms. Speech Communication, 49(7), 588–601.CrossRefGoogle Scholar
  2. 2.
    Loizou, P. (2017). NOIZEUS: A noisy speech corpus for evaluation of speech enhancement algorithms. Speech Communication, 49, 588–601.Google Scholar
  3. 3.
    Hu, Y., & Loizou, P. C. (2008). Evaluation of objective quality measures for speech enhancement. IEEE Transactions on Audio, Speech and Language Processing, 16(1), 229–238.CrossRefGoogle Scholar
  4. 4.
    Martin, R. (2005). Speech enhancement based on minimum mean-square error estimation and supergaussian priors. IEEE Transactions on Speech and Audio Processing, 13(5), 845–856.CrossRefGoogle Scholar
  5. 5.
    Lotter, T., & Vary, P. (2005). Speech enhancement by MAP spectral amplitude estimation using a super-Gaussian speech model. EURASIP Journal on Applied Signal Processing, 2005, 1110–1126.zbMATHGoogle Scholar
  6. 6.
    Loizou, P. C. (2005). Speech enhancement based on perceptually motivated Bayesian estimators of the magnitude spectrum. IEEE Transactions on Speech and Audio Processing, 13(5), 857–869.CrossRefGoogle Scholar
  7. 7.
    Loizou, P. C., & Kim, G. (2011). Reasons why current speech-enhancement algorithms do not improve speech intelligibility and) suggested solutions. IEEE Transactions on Audio, Speech and Language Processing, 19(1), 47–56.CrossRefGoogle Scholar
  8. 8.
    Cohen, I. (2005). Relaxed statistical model for speech enhancement and a priori SNR estimation. IEEE Transactions on Speech and Audio Processing, 13(5), 870–881.CrossRefGoogle Scholar
  9. 9.
    Ghanbari, Y., & Karami-Mollaei, M. R. (2006). A new approach for speech enhancement based on the adaptive thresholding of the wavelet packets. Speech Communication, 48(8), 927–940.CrossRefGoogle Scholar
  10. 10.
    Mohammadiha, N., Smaragdis, P., & Leijon, A. (2013). Supervised and unsupervised speech enhancement using nonnegative matrix factorization. IEEE Transactions on Audio, Speech and Language Processing, 21(10), 2140–2151.CrossRefGoogle Scholar
  11. 11.
    Cohen, I. (2005). Speech enhancement using super-Gaussian speech models and noncausal a priori SNR estimation. Speech Communication, 47(3), 336–350.CrossRefGoogle Scholar
  12. 12.
    Skowronski, M. D., & Harris, J. G. (2006). Applied principles of clear and Lombard speech for automated intelligibility enhancement in noisy environments. Speech Communication, 48(5), 549–558.CrossRefGoogle Scholar
  13. 13.
    Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time–frequency weighted noisy speech. IEEE Transactions on Audio, Speech and Language Processing, 19(7), 2125–2136.CrossRefGoogle Scholar
  14. 14.
    Shao, Y., & Chang, C.-H. (2007). A generalized time–frequency subtraction method for robust speech enhancement based on wavelet filter banks modeling of the human auditory system. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 37(4), 877–889.CrossRefGoogle Scholar
  15. 15.
    Lu, Y., & Cooke, M. (2009). The contribution of changes in F0 and spectral tilt to increased intelligibility of speech produced in noise. Speech Communication, 51(12), 1253–1262.CrossRefGoogle Scholar
  16. 16.
    Hansen, J. H., Radhakrishnan, V., & Arehart, K. H. (2006). Speech enhancement based on generalized minimum mean square error estimators and masking properties of the auditory system. IEEE Transactions on Audio, Speech and Language Processing, 14(6), 2049–2063.CrossRefGoogle Scholar
  17. 17.
    Taghia, J., & Martin, R. (2014). Objective intelligibility measures based on mutual information for speech subjected to speech enhancement processing. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 22(1), 6–16.CrossRefGoogle Scholar
  18. 18.
    Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2015). A regression approach to speech enhancement based on deep neural networks. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 23(1), 7–19.CrossRefGoogle Scholar
  19. 19.
    Kim, G., & Loizou, P. C. (2010). Improving speech intelligibility in noise using environment-optimized algorithms. IEEE Transactions on Audio, Speech and Language Processing, 18(8), 2080–2090.CrossRefGoogle Scholar
  20. 20.
    Jokinen, E., Takanen, M., Vainio, M., & Alku, P. (2014). An adaptive post-filtering method producing an artificial Lombard-like effect for intelligibility enhancement of narrowband telephone speech. Computer Speech & Language, 28(2), 619–628.CrossRefGoogle Scholar
  21. 21.
    Petkov, P. N., Henter, G. E., & Kleijn, W. B. (2013). Maximizing phoneme recognition accuracy for enhanced speech intelligibility in noise. IEEE Transactions on Audio, Speech and Language Processing, 21(5), 1035–1045.CrossRefGoogle Scholar
  22. 22.
    Tsao, Yu., & Lai, Y.-H. (2016). Generalized maximum a posteriori spectral amplitude estimation for speech enhancement. Speech Communication, 76, 112–126.CrossRefGoogle Scholar
  23. 23.
    Chen, F. (2016). Predicting the intelligibility of noise-corrupted speech non-intrusively by across-band envelope correlation. Biomedical Signal Processing and Control, 24, 109–113.CrossRefGoogle Scholar
  24. 24.
    Zorilă, T.-C., Stylianou, Y., Ishihara, T., & Akamine, M. (2016). Near and far field speech-in-noise intelligibility improvements based on a time–frequency energy reallocation approach. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 24(10), 1808–1818.CrossRefGoogle Scholar
  25. 25.
    Goehring, T., Bolner, F., Monaghan, J. J. M., Dijk, B. V., Zarowski, A., & Bleeck, S. (2017). Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users. Hearing Research, 344, 183–194.CrossRefGoogle Scholar
  26. 26.
    Kolbæk, M., Tan, Z.-H., & Jensen, J. (2017). Speech intelligibility potential of general and specialized deep neural network based speech enhancement systems. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(1), 153–167.CrossRefGoogle Scholar
  27. 27.
    Loizou, P. C. (2013). Speech enhancement: Theory and practice. New York: CRC Press.CrossRefGoogle Scholar
  28. 28.
    Samui, S., Chakrabarti, I., & Ghosh, S. K. (2016). Improved single channel phase-aware speech enhancement technique for low signal-to-noise ratio signal. IET Signal Processing, 10(6), 641–650.CrossRefGoogle Scholar
  29. 29.
    Ozaki, Y., Yano, M., & Onishi, M. (2017). Effective hyperparameter optimization using Nelder-Mead method in deep learning. IPSJ Transactions on Computer Vision and Applications, 9, 20.CrossRefGoogle Scholar
  30. 30.
    Hori, T., Chen, Z., Erdogan, H., Hershey, J. R., Roux, J. L., Mitra, V., et al. (2017). Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend. Berlin: Springer.CrossRefGoogle Scholar
  31. 31.
    An efficient MFCC extraction method in speech recognitionGoogle Scholar
  32. 32.
    Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2014). Global variance equalization for improving deep neural network based speech enhancement. In IEEE China summit & international conference on signal and information processing (China SIP), 2014 (pp. 71–75). IEEE.Google Scholar
  33. 33.
    Zue, V., Seneff, S., & Glass, J. (1990). Speech database development at MIT: Timit and beyond. Speech Communication, 9(4), 351–356.CrossRefGoogle Scholar
  34. 34.
    Kavalekalam, S. M., Christensen, M. G., Gran, F., & Boldt, J. B. (2016). Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach. In IEEE international conference on acoustics, speech and signal processing (ICASSP), 2016 (pp. 191–195). IEEE.Google Scholar
  35. 35.
    Kirubagari, B., Palanivel, S., & Subathra, N. (2014). Speech enhancement using minimum mean square error filter and spectral subtraction filter. In International conference on information communication and embedded systems (ICICES), 2014 (pp. 1–7). IEEE.Google Scholar
  36. 36.
    Hu, Y., & Loizou, P. C. (2003). A generalized subspace approach for enhancing speech corrupted by colored noise. IEEE Transactions on Speech and Audio Processing, 11(4), 334–341.CrossRefGoogle Scholar
  37. 37.
    Ephraim, Y., & Malah, D. (1985). Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(2), 443–445.CrossRefGoogle Scholar
  38. 38.
    Liu, B., Tao, J., Wen, Z., & Mo, F. (2016). Speech enhancement based on analysis-synthesis framework with improved parameter domain enhancement. Journal of Signal Processing Systems, 82(2), 141–150.CrossRefGoogle Scholar
  39. 39.
    Hirsch, H. G., & Pearce, D. (2000). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In ASR2000-automatic speech recognition: Challenges for the new Millenium ISCA tutorial and research workshop (ITRW).Google Scholar
  40. 40.
    Rix, A. W., Beerends, J. G., Hollier, M. P., & Hekstra, A. P. (2001). Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In 2001 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 01CH37221) (Vol. 2, pp. 749–752).Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Electronics and Communication EngineeringBirla Institute of TechnologyMesraIndia
  2. 2.Electronics and Telecom EngineeringCV Raman College of EngineeringBhubaneswarIndia

Personalised recommendations