Abstract
Speech intelligibility is a significant factor for successful speech communication. To enhance the intelligibility, many methods have been proposed, mainly by operating the speech signal such as increasing the amplitude or modifying the speech spectrum. However, their effects are limited when the background noise is extremely strong. In this paper, we purpose a preprocessed noise cancellation model to enhance the speech intelligibility by predicting the cancelling signal and superimposing it into the speech signal. We build a deep neural network (DNN) model to make the prediction algorithm have better accuracy. Finally, the effectiveness of the algorithm was verified by objective and subjective tests, the average of signal-to-noise ratio (SNR) improved 4.5 dB, the average of speech intelligibility index (SII) increased 5.4% and the average of comparison mean opinion score (CMOS) rose 1.16 on a variety of test cases.
X. Wang—This work is supported by National Nature Science Foundation of China (No. 61231015, 61671335); National High Technology Research and Development Program of China (863 Program) No. 2015AA016306; Hubei Province Technological Innovation Major Project (No. 2016AAA015).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Niederjohn, R., Grotelueschen, J.: The enhancement of speech intelligibility in high noise levels by high-pass filtering followed by rapid amplitude compression. IEEE Trans. Acoust. Speech Signal Process. 24(4), 277–282 (1976)
Niederjohn, R., Grotelueschen, J.: Speech intelligibility enhancement in a power generating noise environment. IEEE Trans. Acoust. Speech Signal Process. 26(4), 378–380 (1978)
Sauert, B., Vary, P.: Near end listening enhancement: Speech intelligibility improvement in noisy environments. In: IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2006. IEEE, vol. 1, pp. I-I (2006)
Zorila, T.C., Kandia, V., Stylianou, Y.: Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression. In: Thirteenth Annual Conference of the International Speech Communication Association (2012)
Schepker, H.F., Rennies, J., Doclo, S.: Improving speech intelligibility in noise by SII-dependent preprocessing using frequency-dependent amplification and dynamic range compression. In: INTERSPEECH. pp. 3577–3581 (2013)
Petkov, P.N., Kleijn, W.B.: Spectral dynamics recovery for enhanced speech intelligibility in noise. IEEE/ACM Trans. Audio, Speech Lang. Process. (TASLP) 23(2), 327–338 (2015)
Goli, P., Karami-mollaei, M.R.: Speech intelligibility improvement in noisy environments based on energy correlation in frequency bands. Digit. Signal Proc. 62, 238–248 (2017)
ANSI A. S3.: 5–1997, Methods for the calculation of the speech intelligibility index. New York: American National Standards Institute, 19, 90–119 (1997)
Widrow, B., Glover, J.R., McCool, J.M., et al.: Adaptive noise cancelling: Principles and applications. Proc. IEEE 63(12), 1692–1716 (1975)
Guarnaccia, C.: Advanced tools for traffic noise modelling and prediction. WSEAS Trans. Syst. 12(2), 121–130 (2013)
Varga, A., Steeneken, H.J.M., Tomlinson, M., et al.: The NOISEX-92 study on the effect of additive noise on automatic speech recognition. Technical Report, DRA Speech Research Unit (1992)
ETSI TS 103 224: A sound field reproduction method for terminal testing including a background noise database. European Telecommunications Standards Institute (2014)
Zue, V., Seneff, S., Glass, J.: Speech database development at MIT: TIMIT and beyond. Speech Commun. 9(4), 351–356 (1990)
Recommendation I. 800: Methods for subjective determination of transmission quality. International Telecommunication Union (1996)
Khademi, S., Hendriks, R.C., Kleijn, W.B.: Jointly optimal near-end and far-end multi-microphone speech intelligibility enhancement based on mutual information. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 654–658 (2016)
Petkov, P.N., Stylianou, Y.: Adaptive Gain Control for Enhanced Speech Intelligibility Under Reverberation[J]. IEEE Signal Process. Lett. 23(10), 1434–1438 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Cheng, F., Wang, X., Gang, L., Tu, W., Wang, J. (2018). Speech Intelligibility Enhancement in Strong Mechanical Noise Based on Neural Networks. In: Zeng, B., Huang, Q., El Saddik, A., Li, H., Jiang, S., Fan, X. (eds) Advances in Multimedia Information Processing – PCM 2017. PCM 2017. Lecture Notes in Computer Science(), vol 10736. Springer, Cham. https://doi.org/10.1007/978-3-319-77383-4_69
Download citation
DOI: https://doi.org/10.1007/978-3-319-77383-4_69
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77382-7
Online ISBN: 978-3-319-77383-4
eBook Packages: Computer ScienceComputer Science (R0)