Acceleration of rank-constrained spatial covariance matrix estimation for blind speech extraction

In this paper, we propose new accelerated update rules for rank-constrained spatial covariance model estimation, which efficiently extracts a directional target source in diffuse background noise. The naive update rule requires heavy computation such as matrix inversion or matrix multiplication. We...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC ... (Online) s. 332 - 338
Hlavní autoři: Kubo, Yuki, Takamune, Norihiro, Kitamura, Daichi, Saruwatari, Hiroshi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.11.2019
Témata:
Acceleration
Computational complexity
Computational modeling
Covariance matrices
Eigenvalues and eigenfunctions
Estimation
Time-frequency analysis
ISSN:2640-0103
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we propose new accelerated update rules for rank-constrained spatial covariance model estimation, which efficiently extracts a directional target source in diffuse background noise. The naive update rule requires heavy computation such as matrix inversion or matrix multiplication. We resolve this problem by expanding matrix inversion to reduce computational complexity; in the parameter update step, we need neither matrix inversion nor multiplication. In an experiment, we show that the proposed accelerated update rule achieves 87 times faster calculation than the naive one.
ISSN:2640-0103
DOI:10.1109/APSIPAASC47483.2019.9023281