Spectral Tilt Estimation for Speech Intelligibility Enhancement Using RNN Based on All-Pole Model

  • Rui Zhang
  • Ruimin HuEmail author
  • Gang Li
  • Xiaochen Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11296)


Speech intelligibility enhancement is extremely meaningful for successful speech communication in noisy environments. Several methods based on Lombard effect are used to increase intelligibility. In those methods, spectral tilt has been suggested to be a significant characteristic to produce Lombard speech that is more intelligible than normal speech. All-pole model computed by some methods has been used to capture the accurate spectral tilt of high-quality speech, but they are not appropriate for the spectral tilt estimation of telephone speech. In this paper, recurrent neural networks (RNNs) are used to estimate the tilt of telephone speech in German and English. RNN-based spectral tilt estimation show the robustness on the change of the all-pole model order and phonation type for narrow and wideband speech. Mean squared error (MSE) of spectral tilt estimation using RNN-based method is increased by about 26.20% in narrow speech and 19.49% in wideband speech comparing to the DNN-based measure.


Spectral tilt All-pole model RNN 



This work is supported by National Key Program of China (No. 2017YFB1002803) and National Nature Science Foundation of China (No. U1736206, No. 61801334, No. 61762005).


  1. 1.
    Kleijn, W.B., Crespo, J.B., Hendriks, R.C., et al.: Optimizing speech intelligibility in a noisy environment: a unified view. IEEE Signal Process. Mag. 32(2), 43–54 (2015)CrossRefGoogle Scholar
  2. 2.
    Sauert, B., Vary, P.: Near end listening enhancement optimized with respect to speech intelligibility index. In: 17th European Signal Processing Conference, pp. 1844–1848. IEEE (2009)Google Scholar
  3. 3.
    Schepker, H., Rennies, J., Doclo, S.: Improving speech intelligibility in noise by SII-dependent preprocessing using frequency-dependent amplification and dynamic range compression. In: Proceedings of Interspeech, pp. 3577–3581. ISCA, Lyon (2013)Google Scholar
  4. 4.
    Petkov, P.N., Kleijn, W.B.: Spectral dynamics recovery for enhanced speech intelligibility in noise. IEEE/ACM Trans. Audio Speech Lang. Process. 23(2), 327–338 (2015)CrossRefGoogle Scholar
  5. 5.
    Petko, P.N., Stylinaou, Y.: Adaptive gain control and time warp for enhanced speech intelligibility under reverberation. In: IEEE International Conference on Acoustic, Speech and Signal Processing (IASSP), New Orleans, pp. 691–695. IEEE (2017)Google Scholar
  6. 6.
    Zorilâ, T.C., Kandia, V., Stylianou, Y.: Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression. In: Proceedings Interspeech, pp. 635–638. ISCA, Portland (2012)Google Scholar
  7. 7.
    Zorilâ, T.C., Stylianou, Y., Ishihara, T., et al.: Near and far field speech-in-noise intelligibility improvements based on a time-frequency energy reallocation approach. IEEE Trans. Audio Speech Lang. Process. 24(10), 1808–1818 (2016)CrossRefGoogle Scholar
  8. 8.
    Jokinen, E., Remes, U., Takanen, M., et al: Spectral tilt modelling with GMMs for intelligibility enhancement of narrowband telephone speech. In: Proceedings of Interspeech, pp. 2036–2040. ISCA, Singapore (2014)Google Scholar
  9. 9.
    Jokinen, E., Remes, U., Alku, P.: The use of read versus conversational Lombard speech in spectral tilt modeling for intelligibility enhancement in near-end noise conditions. In: Proceedings of Interspeech, pp. 2771–2775. ISCA, San Francisco (2016)Google Scholar
  10. 10.
    Jokinen, E., Remes, U., Alku, P.: Intelligibility enhancement of telephone speech using gaussian process regression for normal-to-lombard spectral tilt conversion. IEEE Trans. Audio Speech Lang. Process. 25(10), 1985–1996 (2017)CrossRefGoogle Scholar
  11. 11.
    Summers, W.V., Pisoni, D.B., Bernacki, R.H., et al.: Effects of noise on speech production: acoustic and perceptual analyses. J. Acoust. Soc. Am. 3(84), 917–928 (1988)CrossRefGoogle Scholar
  12. 12.
    Bronkhorst, A.W.: The cocktail party phenomenon: a review of research on speech intelligibility in multiple-talker conditions. Acta Acust. United Acust. 86(1), 117–128 (2000)Google Scholar
  13. 13.
    Lu, Y., Cooke, M.: The contribution of change in F0 and spectral tilt to increased intelligibility of speech produced in noise. Speech Commun. 51(12), 1253–1262 (2009)CrossRefGoogle Scholar
  14. 14.
    Cooke, M., Lu, Y.: Spectral and temporal changes to speech produced in the presence of energetic and informational masker. J. Acoust. Soc. Am. 128(4), 2059–2069 (2010)CrossRefGoogle Scholar
  15. 15.
    Jokinen, E., Alku, P.: Estimating the spectral tilt of the glottal source from telephone speech using neural network. J. Acoust. Soc. Am. Express Lett. 141(4), 327–330 (2017)CrossRefGoogle Scholar
  16. 16.
    Makhoul, J.: Linear prediction: a tutorial review. Proc. IEEE 63(4), 561–580 (1975)CrossRefGoogle Scholar
  17. 17.
    El-Jaroudi, A., Makhoul, J.: Discrete all-pole modeling. IEEE Trans. Signal Process. 39(2), 411–423 (1991)CrossRefGoogle Scholar
  18. 18.
    Ma, C., Kamp, Y., Willems, L.F.: Robust signal selection for linear prediction analysis of voiced speech. Speech Commun. 12(1), 69–81 (1993)CrossRefGoogle Scholar
  19. 19.
    Magi, C., Pohjalainen, J.: Stabilised weighted linear prediction. Speech Commun. 51(5), 401–411 (2009)CrossRefGoogle Scholar
  20. 20.
    Airaksinen, M., Story, B., Alku, P.: Quasi closed phase analysis for glottal inverse filtering. In: 14th Annual Conference of the International Speech Communication Association, pp. 143–147. ISCA, Lyon (2013)Google Scholar
  21. 21.
    Airaksinen, M., Raitio, T., Story, B., et al.: Quasi closed phase glottal inverse filtering analysis with weighted linear prediction. IEEE Trans. Audio Speech Lang. Process. 22(3), 596–607 (2014)CrossRefGoogle Scholar
  22. 22.
    Drugman, T., Thomas, M., Gudnason, J., et al.: Detection of glottal closure instants from speech signal: a quantitative review. IEEE Trans. Audio Speech Lang. Process. 20(3), 994–1006 (2012)CrossRefGoogle Scholar
  23. 23.
    Sofoklis, K., Okko, R., Pavvo, A.: Evaluation of spectral tilt measures for sentence prominence under different noise conditions. In: Proceedings of Interspeech, pp. 3211–3215. ISCA, Stockholm (2017)Google Scholar
  24. 24.
    Lopez, A.R., Seshadri, S., Juvela, L., et al.: Speaking style conversion from normal to Lombard speech using a glottal vocoder and Bayesian GMMs. In: Proceedings of Interspeech, pp. 1363–1367. ISCA, Stockholm (2017)Google Scholar
  25. 25.
    Tsoi, A.C., Back, A.: Discrete time recurrent neural network architectures: a unifying review. Neurocomputing 15(3–4), 183–223 (1997)CrossRefGoogle Scholar
  26. 26.
    Sołoducha, M., Raake, A., Kettler, F., Voigt, P.: Lombard speech database for German language. In: Proceedings of DAGA, Aachen (2016)Google Scholar
  27. 27.
    Cooke, M., Mayo, C., Valentini-Botinhao, C., et al.: Evaluating the intelligibility benefit of speech modifications in known noise conditions. Speech Commun. 55(4), 572–585 (2013)CrossRefGoogle Scholar
  28. 28.
    Rothauser, E.H.: IEEE recommended practice for speech quality measurements. IEEE Trans. Audio Electroacoust. 17, 225–246 (1969)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Rui Zhang
    • 1
    • 2
  • Ruimin Hu
    • 1
    • 2
    Email author
  • Gang Li
    • 1
    • 2
  • Xiaochen Wang
    • 1
    • 3
  1. 1.National Engineering Research Center for Multimedia Software, School of Computer ScienceWuhan UniversityWuhanChina
  2. 2.Hubei Key Laboratory of Multimedia and Network Communication EngineeringWuhan UniversityWuhanChina
  3. 3.Collaborative Innovation Center of Geospatial TechnologyWuhanChina

Personalised recommendations