---
_id: '44326'
abstract:
- lang: eng
  text: "Low-quality models that miss relevant dynamics lead to major challenges in
    modelbased\r\nstate estimation. We address this issue by simultaneously estimating
    the system’s states\r\nand its model inaccuracies by a square root unscented Kalman
    filter (SRUKF). Concretely,\r\nwe augment the state with the parameter vector
    of a linear combination containing suitable\r\nfunctions that approximate the
    lacking dynamics. Presuming that only a few dynamical terms\r\nare relevant, the
    parameter vector is claimed to be sparse. In Bayesian setting, properties like\r\nsparsity
    are expressed by a prior distribution. One common choice for sparsity is a Laplace\r\ndistribution.
    However, due to disadvantages of a Laplacian prior in regards to the SRUKF,\r\nthe
    regularized horseshoe distribution, a Gaussian that approximately features sparsity,
    is\r\napplied instead. Results exhibit small estimation errors with model improvements
    detected by\r\nan automated model reduction technique."
author:
- first_name: Ricarda-Samantha
  full_name: Götte, Ricarda-Samantha
  id: '43992'
  last_name: Götte
- first_name: Julia
  full_name: Timmermann, Julia
  id: '15402'
  last_name: Timmermann
citation:
  ama: 'Götte R-S, Timmermann J. Approximating a Laplacian Prior for Joint State and
    Model Estimation within an UKF. In: <i>IFAC-PapersOnLine</i>. Vol 56. ; 2023:869-874.'
  apa: Götte, R.-S., &#38; Timmermann, J. (2023). Approximating a Laplacian Prior
    for Joint State and Model Estimation within an UKF. <i>IFAC-PapersOnLine</i>,
    <i>56</i>(2), 869–874.
  bibtex: '@inproceedings{Götte_Timmermann_2023, title={Approximating a Laplacian
    Prior for Joint State and Model Estimation within an UKF}, volume={56}, number={2},
    booktitle={IFAC-PapersOnLine}, author={Götte, Ricarda-Samantha and Timmermann,
    Julia}, year={2023}, pages={869–874} }'
  chicago: Götte, Ricarda-Samantha, and Julia Timmermann. “Approximating a Laplacian
    Prior for Joint State and Model Estimation within an UKF.” In <i>IFAC-PapersOnLine</i>,
    56:869–74, 2023.
  ieee: R.-S. Götte and J. Timmermann, “Approximating a Laplacian Prior for Joint
    State and Model Estimation within an UKF,” in <i>IFAC-PapersOnLine</i>, Yokohama,
    Japan, 2023, vol. 56, no. 2, pp. 869–874.
  mla: Götte, Ricarda-Samantha, and Julia Timmermann. “Approximating a Laplacian Prior
    for Joint State and Model Estimation within an UKF.” <i>IFAC-PapersOnLine</i>,
    vol. 56, no. 2, 2023, pp. 869–74.
  short: 'R.-S. Götte, J. Timmermann, in: IFAC-PapersOnLine, 2023, pp. 869–874.'
conference:
  end_date: 2023-07-14
  location: Yokohama, Japan
  name: 22nd IFAC World Congress
  start_date: 2023-07-09
date_created: 2023-05-02T15:16:43Z
date_updated: 2024-11-13T08:42:37Z
department:
- _id: '153'
- _id: '880'
intvolume: '        56'
issue: '2'
keyword:
- joint estimation
- unscented Kalman filter
- sparsity
- Laplacian prior
- regularized horseshoe
- principal component analysis
language:
- iso: eng
page: 869-874
publication: IFAC-PapersOnLine
quality_controlled: '1'
status: public
title: Approximating a Laplacian Prior for Joint State and Model Estimation within
  an UKF
type: conference
user_id: '43992'
volume: 56
year: '2023'
...
---
_id: '11930'
abstract:
- lang: eng
  text: For human-machine interfaces in distant-talking environments multichannel
    signal processing is often employed to obtain an enhanced signal for subsequent
    processing. In this paper we propose a novel adaptation algorithm for a filter-and-sum
    beamformer to adjust the coefficients of FIR filters to changing acoustic room
    impulses, e.g. due to speaker movement. A deterministic and a stochastic gradient
    ascent algorithm are derived from a constrained optimization problem, which iteratively
    estimates the eigenvector corresponding to the largest eigenvalue of the cross
    power spectral density of the microphone signals. The method does not require
    an explicit estimation of the speaker location. The experimental results show
    fast adaptation and excellent robustness of the proposed algorithm.
author:
- first_name: Ernst
  full_name: Warsitz, Ernst
  last_name: Warsitz
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Warsitz E, Haeb-Umbach R. Acoustic filter-and-sum beamforming by adaptive
    principal component analysis. In: <i>IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2005)</i>. Vol 4. ; 2005:iv/797-iv/800 Vol.
    4. doi:<a href="https://doi.org/10.1109/ICASSP.2005.1416129">10.1109/ICASSP.2005.1416129</a>'
  apa: Warsitz, E., &#38; Haeb-Umbach, R. (2005). Acoustic filter-and-sum beamforming
    by adaptive principal component analysis. In <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2005)</i> (Vol. 4, p. iv/797-iv/800
    Vol. 4). <a href="https://doi.org/10.1109/ICASSP.2005.1416129">https://doi.org/10.1109/ICASSP.2005.1416129</a>
  bibtex: '@inproceedings{Warsitz_Haeb-Umbach_2005, title={Acoustic filter-and-sum
    beamforming by adaptive principal component analysis}, volume={4}, DOI={<a href="https://doi.org/10.1109/ICASSP.2005.1416129">10.1109/ICASSP.2005.1416129</a>},
    booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2005)}, author={Warsitz, Ernst and Haeb-Umbach, Reinhold}, year={2005},
    pages={iv/797-iv/800 Vol. 4} }'
  chicago: Warsitz, Ernst, and Reinhold Haeb-Umbach. “Acoustic Filter-and-Sum Beamforming
    by Adaptive Principal Component Analysis.” In <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2005)</i>, 4:iv/797-iv/800
    Vol. 4, 2005. <a href="https://doi.org/10.1109/ICASSP.2005.1416129">https://doi.org/10.1109/ICASSP.2005.1416129</a>.
  ieee: E. Warsitz and R. Haeb-Umbach, “Acoustic filter-and-sum beamforming by adaptive
    principal component analysis,” in <i>IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2005)</i>, 2005, vol. 4, p. iv/797-iv/800
    Vol. 4.
  mla: Warsitz, Ernst, and Reinhold Haeb-Umbach. “Acoustic Filter-and-Sum Beamforming
    by Adaptive Principal Component Analysis.” <i>IEEE International Conference on
    Acoustics, Speech and Signal Processing (ICASSP 2005)</i>, vol. 4, 2005, p. iv/797-iv/800
    Vol. 4, doi:<a href="https://doi.org/10.1109/ICASSP.2005.1416129">10.1109/ICASSP.2005.1416129</a>.
  short: 'E. Warsitz, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2005), 2005, p. iv/797-iv/800 Vol. 4.'
date_created: 2019-07-12T05:31:00Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2005.1416129
intvolume: '         4'
keyword:
- acoustic filter-and-sum beamforming
- acoustic room impulses
- acoustic signal processing
- adaptive principal component analysis
- adaptive signal processing
- architectural acoustics
- constrained optimization problem
- cross power spectral density
- deterministic algorithm
- deterministic algorithms
- distant-talking environments
- eigenvalues and eigenfunctions
- eigenvector
- enhanced signal
- filter-and-sum beamformer
- FIR filter coefficients
- FIR filter coefficients
- FIR filters
- gradient methods
- human-machine interfaces
- iterative estimation
- iterative methods
- largest eigenvalue
- microphone signals
- multichannel signal processing
- optimisation
- principal component analysis
- spectral analysis
- stochastic gradient ascent algorithm
- stochastic processes
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2005/WaHa05.pdf
oa: '1'
page: iv/797-iv/800 Vol. 4
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2005)
status: public
title: Acoustic filter-and-sum beamforming by adaptive principal component analysis
type: conference
user_id: '44006'
volume: 4
year: '2005'
...