Online Acoustic System Identification Exploiting Kalman Filtering and an Adaptive Impulse Response Subspace Model
Tóm tắt
We introduce a novel algorithm for online estimation of Acoustic Impulse Responses (AIRs) which allows for fast convergence by exploiting prior knowledge about the fundamental structure of AIRs. The proposed method assumes that the variability of AIRs of an acoustic scene is confined to a low-dimensional manifold which is embedded in a high-dimensional space of possible AIR estimates. We discuss various approaches which exploit a training data set of AIRs, e.g., high-accuracy AIR estimates from the acoustic scene, to learn a local affine subspace approximation of the AIR manifold. The model is motivated by the idea of describing the generally nonlinear AIR manifold locally by tangential hyperplanes and its validity is verified for simulated data. Subsequently, we describe how the manifold assumption can be used to enhance online AIR estimates by projecting them onto an adaptively estimated subspace. Motivated by the assumption of manifolds being locally Euclidean, the parameters determining the adaptive subspace are learned from the nearest neighbor AIR training samples to the current AIR estimate. To assess the proximity of training data AIRs to the current AIR estimate, we introduce a probabilistic extension of the Euclidean distance which improves the performance for applications with non-white excitation signals. Furthermore, we describe how model imperfections can be tackled by a soft projection of the AIR estimates. The proposed algorithm exhibits significantly faster convergence properties in comparison to a high-performance state-of-the-art algorithm. Furthermore, we show an improved steady-state performance for speech-excited system identification scenarios suffering from high-level interfering noise and nonunique solutions.
Tài liệu tham khảo
Enzner, G., et al. (2014). Acoustic Echo Control, in Academic Press Library in Signal Processing, vol. 4, pp. 807–877. Elsevier.
Diniz, P. S. R. (2007). Adaptive Filtering: Algorithms and Practical Implementation. Springer: Berlin, Heidelberg.
Widrow, B., & Hoff, M. E. (1960). Adaptive Switching Circuits, in WESCON Convention Record (pp. 96–104). Los Angeles, CA: USA, Aug.
Ferrara, E. (1980). Fast implementations of LMS adaptive filters. Transactions on Acoustics, Speech, and Signal Processing, 28(4), 474–475.
Benesty, J., et al. (2006). A Nonparametric VSS NLMS Algorithm. IEEE Signal Processing Letters, 13(10), 581–584.
Kuech, F., et al. (2014). State-space architecture of the partitioned-block-based acoustic echo controller, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1295–1299). Florence: Italy, May.
Haykin, S. (2002). Adaptive Filter Theory (4th ed.). NJ, USA: Prentice Hall.
Hänsler, E., & Schmidt, G. (2004). Acoustic Echo and Noise Control: A practical Approach. NJ, USA: Wiley-Interscience.
Mansour, D., & Gray, A. (1982). Unconstrained frequency-domain adaptive filter. Transactions on Acoustics, Speech, and Signal Processing, 30(5), 726–734.
Benesty, J., et al. (2000). A new class of doubletalk detectors based on cross-correlation. IEEE Transactions on Speech and Audio Processing, 8(2), 168–172.
Nitsch, B. H. (2000). A frequency-selective stepfactor control for an adaptive filter algorithm working in the frequency domain. Signal Processing, 80(9), 1733–1745.
Enzner, G., & Vary, P. (2006). Frequency-domain adaptive Kalman filter for acoustic echo control in hands-free telephones. Signal Processing, 86(6), 1140–1156.
Malik, S., & Enzner, G. (2010). Online maximum-likelihood learning of time-varying dynamical models in block-frequency-domain, in International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas, TX: USA.
Huemmer, C., et al. (2015). The NLMS algorithm with time-variant optimum stepsize derived from a bayesian network perspective. IEEE Signal Processing Letters, 22(11), 1874–1878.
Yang, F., et al. (2017). Frequency-Domain Adaptive Kalman Filter With Fast Recovery of Abrupt Echo-Path Changes. IEEE Signal Processing Letters, 24(12), 1778–1782.
Haubner, T., et al. (2021). Noise-robust adaptation control for supervised acoustic system identification exploiting a noise dictionary, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 945–949). Toronto, ON: Canada, June.
Haubner, T., et al. (2021). A Synergistic Kalman- and Deep Postfiltering Approach to Acoustic Echo Cancellation, in European Signal Processing Conference (EUSIPCO). Dublin: Ireland.
Fozunbal, M., et al. (2008). Multi-Channel Echo Control by Model Learning, in International Workshop on Acoustic Echo and Noise Control (IWAENC). USA: Seattle.
Koren, T., et al. (2012). Supervised system identification based on local PCA models, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 541–544). Kyoto: Japan, Mar.
Talmon, R., & Gannot, S. (2013). Relative transfer function identification on manifolds for supervised GSC beamformers, in European Signal Processing Conference (EUSIPCO). Marrakech: Morocco.
Haubner, T., et al. (2020). Online supervised acoustic system identification exploiting prelearned local affine subspace models, in International Workshop on Machine Learning for Signal Processing (MLSP). Espoo: Finland.
Laufer-Goldshtein, B., et al. (2015). A Study on Manifolds of Acoustic Responses, in Latent Variable Analysis and Signal Separation (LVA/ICA) (pp. 203–210). Liberec: Czech Republic, Aug.
Talmon, R., et al. (2013). Diffusion Maps for Signal Processing: A Deeper Look at Manifold-Learning Techniques Based on Kernels and Graphs. IEEE Signal Processing Magazine, 30(4), 75–86.
Jolliffe, I. T. (1986). Principal components in regression analysis, in Principal component analysis, pp. 129–155. Springer.
Hahmann, M., et al. (2019). Analysis of a sound field in a room using dictionary learning, in 23rd International Congress on Acoustics (ICA). Aachen: Germany.
Sondhi, M. M., et al. (1995). Stereophonic acoustic echo cancellation-an overview of the fundamental problem. IEEE Signal Processing Letters, 2(8), 148–151.
Benesty, J., et al. (1998). A better understanding and an improved solution to the specific problems of stereophonic acoustic echo cancellation. IEEE Transactions on Speech and Audio Processing, 6(2), 156–165.
Malik, S., & Enzner, G. (2011). Recursive Bayesian Control of Multichannel Acoustic Echo Cancellation. IEEE Signal Processing Letters, 18(11), 619–622.
Tu, L. W. (2010). An Introduction to Manifolds. New York: Universitext. Springer.
Strang, G. (2006). Linear Algebra and its Applications. Brooks/Cole, Belmont, CA: Thomson.
Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129–137.
Arthur, D., & Vassilvitskii, V. (2007). K-means++: The advantages of careful seeding, in Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms. New Orleans, LA: USA.
Bishop, C. M. (2007). Pattern Recognition and Machine Learning (Information Science and Statistics). Springer: Berlin, Heidelberg.
Buchner, H., et al. (2005). Generalized multichannel frequency-domain adaptive filtering: efficient realization and application to hands-free speech communication. Signal Processing, 85(3), 549–570.
Dietzen, T., et al. (2016). Partitioned block frequency domain Kalman filter for multi-channel linear prediction based blind speech dereverberation, in 2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC). Xi’an: China
Franzen, J., & Fingscheidt, T. (2019). Improved Measurement Noise Covariance Estimation for N-channel Feedback Cancellation Based on the Frequency Domain Adaptive Kalman Filter, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 965–969). Brighton: United Kingdom, May.
Petersen, K. B., & Pedersen, M. S. (2012). The matrix cookbook, Version 20121115.
Allen, J. B., & Berkley, D. A. (1979). Image method for efficiently simulating small-room acoustics. Journal of the Acoustical Society of America, 65(4), 943–950.
Habets, E. (2010). Room Impulse Response Generator. Tech. Rep.: Technische Universiteit Eindhoven.
Panfili, L. M., et al. (2017). The UW/NU corpus, version 2.0, https://depts.washington.edu/phonlab/projects/uwnu.php.