Deep Neural Network Based Speech Enhancement

  • Rashmirekha Ram
  • Mihir Narayan MohantyEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 768)


Enhancement of the speech signal is an essential task in the adverse environment. Several algorithms have been designed from several years to improve the quality. Mostly Neural Network and its variants are utilized for classification purpose. This paper exhibits the speech enhancement method based on the Deep Neural Network (DNN) to improve the quality and to increase the Signal-to-Noise Ratio of the speech signal. Different hidden layers are set to test the results. The audio features are extracted by using the short time Fourier transforms. The use of audio features improves the speech enhancement performance of DNN. Segmental Signal-to-Noise Ratio (SegSNR) and Perceptual Evaluation of Speech Quality (PESQ) are measured to test the results.


Deep neural network Adaptive linear neuron Perceptual evaluation of speech quality Segmental signal-to-noise ratio Neural network Speech enhancement 


  1. 1.
    Loizou, P.: Speech Enhancement: Theory and Practice. CRC Press, Boca Raton (2007)Google Scholar
  2. 2.
    Haykin, S.: Adaptive Filter Theory, 3rd edn. Prentice Hall, Upper Saddle River (1996)zbMATHGoogle Scholar
  3. 3.
    Boll, S.F.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. ASSP 27, 113–120 (1979)CrossRefGoogle Scholar
  4. 4.
    Chaudhari, A., Dhonde, S.B.: A review on speech enhancement techniques. In: International Conference on Pervasive Computing (ICPC) (2015)Google Scholar
  5. 5.
    Vihari, S., Murthy, A.S., Soni, P., Naik, D.C.: Comparison of speech enhancement algorithms. Procedia Comput. Sci. 89, 666–676 (2016)CrossRefGoogle Scholar
  6. 6.
    Ram, R., Mohanty, M.N.: Performance analysis of adaptive algorithms for speech enhancement applications. Indian J. Sci. Technol. 9(44), 6 (2016)CrossRefGoogle Scholar
  7. 7.
    Fah, L.B., Hussain, A., Samad, S.A.: Speech enhancement by noise cancellation using neural network. In: IEEE Conference on TENCON (2000)Google Scholar
  8. 8.
    Daqrouq, K., Abu-Isbeih, I.N., Alfauori, M.: Speech signal enhancement using neural network and wavelet transform. In: International Multi-Conference on Systems, Signals and Devices (2009)Google Scholar
  9. 9.
    Ram, R., Mohanty, M.N.: Fractional DCT ADALINE method for speech enhancement. In: International Conference on Machine Learning and Computational Intelligence (2017) (Communicated)Google Scholar
  10. 10.
    Goehring, T., Bolner, F., Monaghan, J.J.M., Dijk, B., Zarowski, A., Bleeck, S.: Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users. Hear. Res. 344, 183–194 (2017)CrossRefGoogle Scholar
  11. 11.
    Prieto, A., Prieto, B., Ortigosa, E.M., Ros, E., Pelayo, F., Ortega, J., Rojas, I.: Neural networks: an overview of early research, current frameworks and new challenges. Neurocomputing 214, 242–268 (2016)CrossRefGoogle Scholar
  12. 12.
    Xu, Y., Du, J., Dai, L., Lee, C.: A regression approach to speech enhancement based on deep neural networks. IEEE/ACM Trans. Audio, Speech, Lang. Process. 23(1), 7–19 (2015)CrossRefGoogle Scholar
  13. 13.
    Li, Y., Kang, S.: Deep neural network based linear predictive parameter estimations for speech enhancement. IET Signal Process. 11(4), 469–476 (2017)CrossRefGoogle Scholar
  14. 14.
    Li, R., Liu, Y., Shi, Y., Dong, L., Cui, W.: ILMSAF based speech enhancement with DNN and noise classification. Speech Commun. 85, 53–70 (2016)CrossRefGoogle Scholar
  15. 15.
    Goehring, T., Yang, X., Monaghan, J.J.M., Bleeck, S.: Speech enhancement for hearing-impaired listeners using deep neural networks with auditory-model based features. In: European Signal Processing Conference (2016)Google Scholar
  16. 16.
    Hou, J.C., Wang, S.S., Lai, Y.H., Lin, J.C., Tsao, Y., Chang, H.W., Wang, H.M.: Audio-visual speech enhancement using deep neural networks. In: IEEE Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1–6 (2016)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringSiksha ‘O’ Anusandhan UniversityBhubaneswarIndia

Personalised recommendations