Abstract
In this paper the problem of detection of impulsive disturbances in archive audio signals is considered. It is shown that semi-causal/noncausal solutions based on joint evaluation of signal prediction errors and leave-one-out signal interpolation errors, allow one to noticeably improve detection results compared to the prediction-only based solutions. The proposed approaches are evaluated on a set of clean audio signals contaminated with real click waveforms extracted from silent parts of old gramophone recordings.
Citations
-
6
CrossRef
-
0
Web of Science
-
8
Scopus
Authors (2)
Cite as
Full text
download paper
downloaded 100 times
- Publication version
- Accepted or Published Version
- License
- Copyright (2017 IEEE)
Keywords
Details
- Category:
- Conference activity
- Type:
- materiały konferencyjne indeksowane w Web of Science
- Title of issue:
- 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) strony 671 - 675
- ISSN:
- 2379-190X
- Language:
- English
- Publication year:
- 2017
- Bibliographic description:
- Ciołek M., Niedźwiecki M..: Detection of impulsive disturbances in archive audio signals, W: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, ,.
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/icassp.2017.7952240
- Bibliography: test
-
- S.V. Vaseghi, Advanced Digital Signal Processing and Noise Reduction, 4th ed. John Wiley and Sons Ltd., 2008. open in new tab
- J.S. Godsill and J.P.W. Rayner, Digital Audio Restora- tion. London, U.K.: Springer, 1998. open in new tab
- S.V. Vaseghi and J.P.W. Rayner, "Detection and suppres- sion of impulsive noise in speech communication sys- tems," IEE Proceedings, vol. 137, pp. 38-46, 1990. open in new tab
- S.V. Vaseghi and R. Frayling-Cork, "Restoration of old gramophone recordings," J. Audio Eng. Soc. vol. 40, no. 10, pp. 791-801, 1992. open in new tab
- P. Esquef, L. Biscainho, P. Diniz, and F. Freeland, "A double-threshold-based approach to impulsive noise de- tection in audio signals," in: Proc. European Signal Pro- cess. Conf., Tampere, Finland, pp. 2041-2044, 2000. open in new tab
- J.S. Godsill and J.P.W. Rayner, "A Bayesian approach to the restoration of degraded audio signals" IEEE Trans. Speech, Audio Process., vol. 3, pp. 267-278, 1995. open in new tab
- J.S. Godsill and P.J.W. Rayner, "Statistical reconstruc- tion and analysis of autoregressive signals in impulsive noise using the Gibbs sampler," IEEE Trans. Speech Au- dio Process., vol. 6, pp. 352-372, 1998. open in new tab
- F.R.Ávila and L.P.W. Biscainho, "Bayesian restoration of audio signals degraded by impulsive noise modeled as individual pulses," IEEE Trans. Audio, Speech Lan- guage Process., vol. 20, pp. 2470-2481, 2012. open in new tab
- M. Niedźwiecki and K. Cisowski, "Adaptive scheme for elimination of broadband noise and impulsive dis- turbances from AR and ARMA signals," IEEE Trans. Audio, Signal Process., vol. 44, pp. 528-537, 1996. open in new tab
- M. Niedźwiecki and M. Ciołek, "Elimination of clicks from archive speech signals using sparse autoregressive modeling," in Proc. 20th Eur. Signal Process. Conf., Bucharest, Romania, pp. 2615-2619, 2012. open in new tab
- M. Niedźwiecki and M. Ciołek, "Localization of impul- sive disturbances in audio signals using template match- ing," Digital Signal Process., vol. 46, pp. 253-265, 2015. open in new tab
- S. Canazza, G. De Poli, and G. Mian, "Restoration of audio documents by means of extended Kalman filter,", IEEE Trans. Audio, Speech Language Process. vol. 18, no. 6, pp. 1107-1115, 2010. open in new tab
- M. Niedźwiecki and M. Ciołek, "Elimination of impul- sive disturbances from archive audio signals using bidi- rectional processing," Trans. Audio Speech Lang. Pro- cess., vol. 21, pp. 1046-1059, 2013. open in new tab
- M. Niedźwiecki, M. Ciołek, and K. Cisowski, "Elim- ination of impulsive disturbances from stereo audio recordings using vector autoregressive modeling and variable-order Kalman filtering," IEEE/ACM Trans. Au- dio Speech Lang. Process., vol. 23, pp. 970-981, 2015. open in new tab
- M. Niedźwiecki and M. Ciołek, "Sparse vector autore- gressive modeling of audio signals and its application to the elimination of impulsive disturbances, in: 17th IFAC Symposium on System Identification, Beijing, China, pp. 1202-1207, 2015.
- M. Ruhland, J. Bitzer, M. Brandt, and S. Goetze, "Reduction of Gaussian, supergaussian, and impulsive noise by interpolation of the binary mask residual," IEEE/ACM Transactions on Audio, Speech, and Lan- guage Processing, vol. 23, no. 10, pp. 1680 -1691, 2015 open in new tab
- R. Tong, Y. Zhou, L. Zhang, G. Bao, and Z. Ye, "A Ro- bust time-frequency decomposition model for suppres- sion of mixed Gaussian-impulse noise in audio signals", IEEE/ACM Transactions on Audio, Speech, and Lan- guage Processing, vol. 23, pp. 69-79, 2015.
- M. Niedźwiecki, "Statistical reconstruction of multivari- ate time series," IEEE Trans. Signal Process., vol. 41, pp. 451-457, 1993. open in new tab
- M. Niedźwiecki, "On the localized estimators and gen- eralized Akaike's criteria" IEEE Trans. Automat. Contr., vol. 29, pp. 970-983, 1981. open in new tab
- T. Söderström and P. Stoica, System Identification. En- glewoods Cliffs NJ: Prentice-Hall, 1988.
- M.S. Kay, Modern Spectral Estimation: Theory and Ap- plication, Englewoods Cliffs NJ: Prentice-Hall, 1988.
- ITU-R Recommendation BS.1387-1, "Method for Objective Measurements of Perceived Audio Quality," 2001. open in new tab
- P. Kabal, "An Examination and Interpretation of ITU- R Recommendation BS.1387: Perceptual Evaluation of Audio Quality," Department of Electrical & Computer Engineering, McGill University, Canada, 2003.
- J. Nuzman, "Audio restoration: An investigation of digital methods for click removal and hiss re- duction", University of Maryland, Institute for Ad- vanced Computer Studies, 2004 [Online]. Available: www.github.com/jnuzman/audio-restoration-2004, last seen in August 2016
- M. Niedźwiecki and M. Ciołek, "Adaptive detection of impulsive disturbances in multivariate signals," submit- ted to IEEE Transactions on Signal Processing. open in new tab
- Verified by:
- Gdańsk University of Technology
seen 91 times