Top

International Journal of Speech Technology

Published in:

31-10-2022

Blind identification of the inverse of SIMO system and deconvolution with Kalman filter

Authors: Tiemin Mei, Guorong He, Yandong Zhao, Jihan Dong

Published in: International Journal of Speech Technology | Issue 4/2022

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

As speech enhancement concerned, blind speech deconvolution are widely used in speech dereverberation, automatic speech recognition and hearing aid designs. it is generally a single-input multiple-output (SIMO) system identification followed by a signal deconvolution. A novel approach, in which blind multichannel identifications of a SIMO system and its inverse system are performed concurrently with Kalman filter, is proposed in this paper. Speech deconvolution is the direct result of the algorithm. The state vector of the Kalman filter is composed of the multichannel impulse responses (MCIRs) of the SIMO system and its inverse system; the measurement equation of the Kalman filter is constructed with the cross relation (CR) among the observed signals and the input-output relation by feeding the deconvolved signal into the identified SIMO system. Comparing with traditional deconvolution methods, the proposed approach is more noise robust and computationally efficient.

previous article Dysarthric speech detection from telephone quality speech using epoch-based pitch perturbation features

next article Universal and accent-discriminative encoders for conformer-based accent-invariant speech recognition

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Ahmad, R., Khong, A. W. H., Hasan, M. K., & Naylor, P. A. (2015). The extended normalized multichannel FLMS algorithm for blind channel identification. In European signal processing conference (pp. 1–5). IEEE

Braun, S., & Habets, E. A. P. (2016). Online dereverberation for dynamic scenarios using a Kalman filter with an autoregressive model. IEEE Signal Processing Letters, 23(12), 1741–1754. https://doi.org/10.1109/LSP.2016.2616888.CrossRef

Braun, S., & Habets, E. A. P. (2018). Linear Prediction based online dereverberation and noise reduction using alternating Kalman filters. IEEE Transactions on Audio, Speech, and Language Processing, 26(6), 1119–1129. https://doi.org/10.1109/TASLP.2018.2811247CrossRef

Furuya, K., Sakauchi, S., & Kataoka, A. (2006). Speech dereverberation by combining MINT-based blind deconvolution and modified sepctral subtraction. In IEEE international conference on acoustics, speech and signal processing (pp. 813–816). https://doi.org/10.1109/ICASSP.2006.1660145

Godard, D. N. (1980). Self-recovering equalization and carrier tracking in two-dimensional data communication systems. IEEE Transactions on Communications, 28(11), 1867–1875. https://doi.org/10.1109/TCOM.1980.1094608CrossRef

Hasan, M. K., Benesty, J., Naylor, P. A., & Ward, D. B. (2005, September). Improving robustness of blind adaptive multichannel identification algorithms using constraints. In Proceedings of the 13th European Signal Processing Conference IEEE.

Haykin, S. (1996). Adaptive filter theory (3rd Ed), (pp. 772–816, pp. 302–321). Prentice-Hall.

He, H., Chen, J., Benesty, J., & Tao, T. (2018). Noise robust frequency-domain adaptive blind multichannel identification with \(\ell _p\)-norm constraint. IEEE Transactions on Audio Speech and Language Processing, 26(9), 1608–1619. https://doi.org/10.1109/TASLP.2018.2835729CrossRef

Huang, Y., & Benesty, J. (2002a). Adaptive blind channel identification: Multi-channel and least mean square and Newton algorithms. IEEE International Conference on Acoustics. https://doi.org/10.1109/ICASSP.2002.5744932CrossRefMATH

Huang, Y., & Benesty, J. (2002b). Adaptive multi-channel least mean square and Newton algorithms for blind channel identification. Signal Processing, 82, 1127–1138. https://doi.org/10.1016/S0165-1684(02)00247-5CrossRefMATH

Huang, Y., & Benesty, J. (2003). A class of frequency-domain adaptive approaches to blind multichannel identification. IEEE Transaction on Signal Processing, 51(1), 11–24. https://doi.org/10.1109/TSP.2002.806559.MathSciNetCrossRefMATH

Liao, L., & Khong, A. W. H. (2010). A noise robust multichannel algorithm for blind estimation of room impulse responses. In Proceedings of the 12th international workshop on acoustic echo and noise control (IWAENC).

Mayyala, Q., Abed-Meraim, K., & Zerguine, A. (2017). Structure-based subspace method for multichannel blind system identification. IEEE Signal Processing Letters, 24(8), 1183–1187. https://doi.org/10.1109/LSP.2017.2715418CrossRef

Mei, T. (2017). Blind multichannel deconvolution with cascaded Kalman filters. DEStech Transactions on Computer Science and Engineering. https://doi.org/10.12783/dtcse/icmsie2017/18663

Mei, T. (2019). Blind multichannel identification based on Kalman filter and eigenvalue decomposition. International Journal of Speech Technology, 22(1), 1–11. https://doi.org/10.1007/s10772-018-09562-wCrossRef

Miyoshi, M., & Kaneda, Y. (1988). Inverse filtering of room acoustics. IEEE Transactions on Acoustics Speech and Signal Processing, 36(2), 145–152. https://doi.org/10.1109/29.1509.CrossRef

Moulines, E., Duhamel, P., Cardoso, J. F., & Mayrargue, S. (1995). Subspace methods for the blind identification of multichannel FIR filters. IEEE Transaction on Signal Processing, 43(2), 516–525. https://doi.org/10.1109/78.348133.CrossRef

Schwartz, B., Gannot, S., & Habets, E. (2015). Online speech dereverberation using Kalman filter and EM algorithm. IEEE Transactions on Audio Speech and Language Processing, 23(2), 394–406. https://doi.org/10.1109/TASLP.2014.2372342CrossRef

Song, S., Cheng, L., Luan, S., Yao, D., & Yan, Y. (2021). An integrated multi-channel approach for joint noise reduction and dereverberation. Applied Acoustics. https://doi.org/10.1016/j.apacoust.2020.107526.CrossRef

Tong, L., Xu, G., & Kailath, T. (1994). Blind identification and equalization based on second-order statistics: A time domain approach. IEEE Transaction on Information Theory, 40(2), 340–349. https://doi.org/10.1109/18.312157.CrossRef

Xu, G., Liu, H., Tong, L., & Kailath, T. (1995). A least-square approach to blind channel identification. IEEE Transactions on Signal Processing, 43(12), 2982–2992. https://doi.org/10.1109/78.476442CrossRef

Title: Blind identification of the inverse of SIMO system and deconvolution with Kalman filter
Authors: Tiemin Mei
Guorong He
Yandong Zhao
Jihan Dong
Publication date: 31-10-2022
Publisher: Springer US
Published in: International Journal of Speech Technology / Issue 4/2022
Print ISSN: 1381-2416
Electronic ISSN: 1572-8110
DOI: https://doi.org/10.1007/s10772-022-10000-1

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Other articles of this Issue 4/2022

Speaker identification using hybrid neural network support vector machine classifier

AI driven human–computer interaction design framework of virtual environment based on comprehensive semantic data analysis with feature extraction

Intelligent automobile auxiliary propagation system based on speech recognition and AI driven feature extraction techniques

Dysarthric speech detection from telephone quality speech using epoch-based pitch perturbation features

Analysis of influencing features with spectral feature extraction and multi-class classification using deep neural network for speech recognition system

Construction of complex environment speech signal communication system based on 5G and AI driven feature extraction techniques