Designing multichannel source separation based on single-channel source separation

Ana Ramirez Lopez; Nobutaka Ono; Ulpu Remes; Kalle Palomäki; Mikko Kurimo

Designing multichannel source separation based on single-channel source separation

Ana Ramirez Lopez, Nobutaka Ono, Ulpu Remes, Kalle Palomäki, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

9 Citations (Scopus)

Abstract

In this paper, an extension of independent vector analysis (IVA), model-based IVA, is proposed for multichannel source separation. For obtaining better source models, we introduce a single-channel source separation method, and utilize the outputs as source variances in time-frequency-variant Gaussian source model. The demixing matrices are estimated in the same way as a state-of-the-art IVA method, auxiliary-function-based IVA (AuxIVA). Experimental evaluations show that the proposed approach is effective and improves the source separation performance of IVA. In addition, several post-filters aiming to realize multichannel Wiener filter (MWF) are investigated. This setup proves to further increase the performance of IVA. The presented method shows a potential to provide a general way to improve the separation performance from single-channel source separation to multichannel source separation.

Original language	English
Title of host publication	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015
Place of Publication	unknown
Publisher	IEEE
Pages	469-473
ISBN (Print)	978-1-4673-6997-8
Publication status	Published - 2015
MoE publication type	A4 Article in a conference publication

Publication series

Name	International Conference on Acoustics Speech and Signal Processing ICASSP
ISSN (Print)	1520-6149

Fingerprint Dive into the research topics of 'Designing multichannel source separation based on single-channel source separation'. Together they form a unique fingerprint.

Cite this

Ramirez Lopez, A., Ono, N., Remes, U., Palomäki, K., & Kurimo, M. (2015). Designing multichannel source separation based on single-channel source separation. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015 (pp. 469-473). (International Conference on Acoustics Speech and Signal Processing ICASSP). IEEE.

Ramirez Lopez, Ana ; Ono, Nobutaka ; Remes, Ulpu ; Palomäki, Kalle ; Kurimo, Mikko. / Designing multichannel source separation based on single-channel source separation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. unknown : IEEE, 2015. pp. 469-473 (International Conference on Acoustics Speech and Signal Processing ICASSP).

@inproceedings{9e78838253864b24a8669b24f16f947f,

title = "Designing multichannel source separation based on single-channel source separation",

abstract = "In this paper, an extension of independent vector analysis (IVA), model-based IVA, is proposed for multichannel source separation. For obtaining better source models, we introduce a single-channel source separation method, and utilize the outputs as source variances in time-frequency-variant Gaussian source model. The demixing matrices are estimated in the same way as a state-of-the-art IVA method, auxiliary-function-based IVA (AuxIVA). Experimental evaluations show that the proposed approach is effective and improves the source separation performance of IVA. In addition, several post-filters aiming to realize multichannel Wiener filter (MWF) are investigated. This setup proves to further increase the performance of IVA. The presented method shows a potential to provide a general way to improve the separation performance from single-channel source separation to multichannel source separation.",

author = "{Ramirez Lopez}, Ana and Nobutaka Ono and Ulpu Remes and Kalle Palom{\"a}ki and Mikko Kurimo",

note = "VK: COIN",

year = "2015",

language = "English",

isbn = "978-1-4673-6997-8",

series = "International Conference on Acoustics Speech and Signal Processing ICASSP",

publisher = "IEEE",

pages = "469--473",

booktitle = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015",

address = "United States",

}

Ramirez Lopez, A, Ono, N, Remes, U, Palomäki, K & Kurimo, M 2015, Designing multichannel source separation based on single-channel source separation. in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. International Conference on Acoustics Speech and Signal Processing ICASSP, IEEE, unknown, pp. 469-473.

Designing multichannel source separation based on single-channel source separation. / Ramirez Lopez, Ana; Ono, Nobutaka; Remes, Ulpu; Palomäki, Kalle; Kurimo, Mikko.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. unknown : IEEE, 2015. p. 469-473 (International Conference on Acoustics Speech and Signal Processing ICASSP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Designing multichannel source separation based on single-channel source separation

AU - Ramirez Lopez, Ana

AU - Ono, Nobutaka

AU - Remes, Ulpu

AU - Palomäki, Kalle

AU - Kurimo, Mikko

N1 - VK: COIN

PY - 2015

Y1 - 2015

N2 - In this paper, an extension of independent vector analysis (IVA), model-based IVA, is proposed for multichannel source separation. For obtaining better source models, we introduce a single-channel source separation method, and utilize the outputs as source variances in time-frequency-variant Gaussian source model. The demixing matrices are estimated in the same way as a state-of-the-art IVA method, auxiliary-function-based IVA (AuxIVA). Experimental evaluations show that the proposed approach is effective and improves the source separation performance of IVA. In addition, several post-filters aiming to realize multichannel Wiener filter (MWF) are investigated. This setup proves to further increase the performance of IVA. The presented method shows a potential to provide a general way to improve the separation performance from single-channel source separation to multichannel source separation.

AB - In this paper, an extension of independent vector analysis (IVA), model-based IVA, is proposed for multichannel source separation. For obtaining better source models, we introduce a single-channel source separation method, and utilize the outputs as source variances in time-frequency-variant Gaussian source model. The demixing matrices are estimated in the same way as a state-of-the-art IVA method, auxiliary-function-based IVA (AuxIVA). Experimental evaluations show that the proposed approach is effective and improves the source separation performance of IVA. In addition, several post-filters aiming to realize multichannel Wiener filter (MWF) are investigated. This setup proves to further increase the performance of IVA. The presented method shows a potential to provide a general way to improve the separation performance from single-channel source separation to multichannel source separation.

M3 - Conference contribution

SN - 978-1-4673-6997-8

T3 - International Conference on Acoustics Speech and Signal Processing ICASSP

SP - 469

EP - 473

BT - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015

PB - IEEE

CY - unknown

ER -

Ramirez Lopez A, Ono N, Remes U, Palomäki K, Kurimo M. Designing multichannel source separation based on single-channel source separation. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. unknown: IEEE. 2015. p. 469-473. (International Conference on Acoustics Speech and Signal Processing ICASSP).