A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems
Quasi-continuous system identification of time-variant linear acoustic systems can be applied in various audio signal processing applications when numerous acoustic transfer functions must be measured. A prominent application is measuring head-related transfer functions. We treat the underlying mult...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Signal Processing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10334061/ |
| _version_ | 1827394123196268544 |
|---|---|
| author | Tobias Kabzinski Peter Jax |
| author_facet | Tobias Kabzinski Peter Jax |
| author_sort | Tobias Kabzinski |
| collection | DOAJ |
| description | Quasi-continuous system identification of time-variant linear acoustic systems can be applied in various audio signal processing applications when numerous acoustic transfer functions must be measured. A prominent application is measuring head-related transfer functions. We treat the underlying multiple-input-multiple-output (MIMO) system identification problem in a state-space model as a joint estimation problem for states, representing impulse responses, and state-space model parameters using the expectation maximization (EM) algorithm. We address limitations of prior work by imposing different model structures, especially for dependencies within a (transformed) state vector. This results in block diagonal matrix structures, for which we derive M-step update rules. Making assumptions about this model structure and choosing a block size for a given application define the computational complexity. In examples, we found that applying this framework yields improvements of up to 10 dB in relative system distance in comparison to a conventional method. |
| first_indexed | 2024-03-08T18:03:37Z |
| format | Article |
| id | doaj.art-b04491f4efd14675bbf069882c525ad9 |
| institution | Directory Open Access Journal |
| issn | 2644-1322 |
| language | English |
| last_indexed | 2024-03-08T18:03:37Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Signal Processing |
| spelling | doaj.art-b04491f4efd14675bbf069882c525ad92024-01-02T00:02:56ZengIEEEIEEE Open Journal of Signal Processing2644-13222024-01-01511212110.1109/OJSP.2023.333772110334061A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic SystemsTobias Kabzinski0https://orcid.org/0000-0003-4428-4722Peter Jax1Institute of Communication Systems (IKS), RWTH Aachen University, Aachen, GermanyInstitute of Communication Systems (IKS), RWTH Aachen University, Aachen, GermanyQuasi-continuous system identification of time-variant linear acoustic systems can be applied in various audio signal processing applications when numerous acoustic transfer functions must be measured. A prominent application is measuring head-related transfer functions. We treat the underlying multiple-input-multiple-output (MIMO) system identification problem in a state-space model as a joint estimation problem for states, representing impulse responses, and state-space model parameters using the expectation maximization (EM) algorithm. We address limitations of prior work by imposing different model structures, especially for dependencies within a (transformed) state vector. This results in block diagonal matrix structures, for which we derive M-step update rules. Making assumptions about this model structure and choosing a block size for a given application define the computational complexity. In examples, we found that applying this framework yields improvements of up to 10 dB in relative system distance in comparison to a conventional method.https://ieeexplore.ieee.org/document/10334061/Expectation maximizationsystem identificationstate-space model |
| spellingShingle | Tobias Kabzinski Peter Jax A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems IEEE Open Journal of Signal Processing Expectation maximization system identification state-space model |
| title | A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems |
| title_full | A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems |
| title_fullStr | A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems |
| title_full_unstemmed | A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems |
| title_short | A Flexible Framework for Expectation Maximization-Based MIMO System Identification for Time-Variant Linear Acoustic Systems |
| title_sort | flexible framework for expectation maximization based mimo system identification for time variant linear acoustic systems |
| topic | Expectation maximization system identification state-space model |
| url | https://ieeexplore.ieee.org/document/10334061/ |
| work_keys_str_mv | AT tobiaskabzinski aflexibleframeworkforexpectationmaximizationbasedmimosystemidentificationfortimevariantlinearacousticsystems AT peterjax aflexibleframeworkforexpectationmaximizationbasedmimosystemidentificationfortimevariantlinearacousticsystems AT tobiaskabzinski flexibleframeworkforexpectationmaximizationbasedmimosystemidentificationfortimevariantlinearacousticsystems AT peterjax flexibleframeworkforexpectationmaximizationbasedmimosystemidentificationfortimevariantlinearacousticsystems |