ssspy 0.1.7

A Python toolkit for sound source separation.

ssspy

A Python toolkit for sound source separation.

Installation

You can install by pip.

pip install ssspy

To install latest version,

pip install git+https://github.com/tky823/ssspy.git

Instead, you can build package from source.

git clone https://github.com/tky823/ssspy.git
cd ssspy
pip install .

If you cannot install ssspy due to failure in building wheel for numpy, please install numpy in advance.

Build Documentation Locally (optional)

To build the documentation locally, you have to include docs and notebooks when installing ssspy.

pip install -e ".[docs,notebooks]"

You need to convert some notebooks by the following command:

# in ssspy/
. ./docs/pre_build.sh

When you build the documentation, run the following command.

cd docs/
make html

Or, you can build the documentation automatically using sphinx-autobuild.

# in ssspy/
sphinx-autobuild docs docs/_build/html

Blind Source Separation Methods

Method	Notebooks
Independent Component Analysis (ICA) [1-3]	Gradient-descent-based ICA: Natural-gradient-descent-based ICA: Fast ICA:
Frequency-Domain Independent Component Analysis (FDICA) [4-6]	Gradient-descent-based FDICA: Natural-gradient-descent-based FDICA: Auxiliary-function-based FDICA (IP1): Auxiliary-function-based FDICA (IP2): Gradient-descent-based Laplace-FDICA: Natural-gradient-descent-based Laplace-FDICA: Auxiliary-function-based Laplace-FDICA (IP1): Auxiliary-function-based Laplace-FDICA (IP2):
Independent Vector Analysis (IVA) [7-14]	Gradient-descent-based IVA: Natural-gradient-descent-based IVA: Fast IVA: Faster IVA: Auxiliary-function-based IVA (IP1): Auxiliary-function-based IVA (IP2): Auxiliary-function-based IVA (ISS1): Auxiliary-function-based IVA (ISS2): Auxiliary-function-based IVA (IPA): Gradient-descent-based Laplace-IVA: Natural-gradient-descent-based Laplace-IVA: Auxiliary-function-based Laplace-IVA (IP1): Auxiliary-function-based Laplace-IVA (IP2): Auxiliary-function-based Laplace-IVA (ISS1): Auxiliary-function-based Laplace-IVA (ISS2): Auxiliary-function-based Laplace-IVA (IPA): Gradient-descent-based Gauss-IVA: Natural-gradient-descent-based Gauss-IVA: Auxiliary-function-based Gauss-IVA (IP1): Auxiliary-function-based Gauss-IVA (IP2): Auxiliary-function-based Gauss-IVA (ISS1): Auxiliary-function-based Gauss-IVA (ISS2): Auxiliary-function-based Gauss-IVA (IPA):
Independent Low-Rank Matrix Analysis (ILRMA) [15-18]	Gauss-ILRMA (IP1/MM): Gauss-ILRMA (IP1/ME): Gauss-ILRMA (IP2/MM): Gauss-ILRMA (IP2/ME): Gauss-ILRMA (ISS1/MM): Gauss-ILRMA (ISS1/ME): Gauss-ILRMA (ISS2/MM): Gauss-ILRMA (ISS2/ME): Gauss-ILRMA (IPA/MM): Gauss-ILRMA (IPA/ME): t-ILRMA (IP1/MM): t-ILRMA (IP1/ME): t-ILRMA (IP2/MM): t-ILRMA (IP2/ME): t-ILRMA (ISS1/MM): t-ILRMA (ISS1/ME): t-ILRMA (ISS2/MM): t-ILRMA (ISS2/ME): GGD-ILRMA (IP1/MM): GGD-ILRMA (IP2/MM): GGD-ILRMA (ISS1/MM): GGD-ILRMA (ISS2/MM):
Independent Positive Semidefinite Tensor Analysis (IPSDTA) [19, 20]	Gauss-IPSDTA (VCD): t-IPSDTA (VCD):
Multichannel Nonnegative Matrix Factorization (MNMF) [21-24]	Gauss-MNMF: t-MNMF: soon Fast Gauss-MNMF (IP1): Fast Gauss-MNMF (IP2):
Blind Source Separation via Primal-Dual Splitting Algorithm (PDS-BSS) [25]	PDS-BSS: PDS-BSS-multiPenalty:
Blind Source Separation via Alternating Direction Method of Multipliers (ADMM-BSS)	ADMM-BSS:
Complex Angular Central Gaussian Mixture Model (cACGMM) [26]	cACGMM:

• [1] P. Comon, "Independent component analysis, a new concept?" Signal Processing, vol. 36, no. 3, pp. 287-314, 1994.
• [2] S. Amari, A. Cichocki, and H. H. Yang, "A new learning algorithm forblind signal separation," in Proc. NIPS, 1996, pp. 757-763.
• [3] A. Hyvärinen, "Fast and robust fixed-point algorithms for independent component analysis," IEEE Trans. on Neural Netw., vol. 10, no. 3, pp. 626-634, 1999.
• [4] N. Murata, S. Ikeda, and A. Ziehe, "An approach to blind source separation based on temporal structure of speech signals," in Neurocomputing, vol. 41, no. 1, pp. 1-24, 2001
• [5] H. Sawada, S. Araki, and S. Makino, "Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment," 2011.
• [6] N. Ono and S. Miyabe, "Auxiliary-function-based independent componentanalysis for super-Gaussian sources," in Proc. LVA/ICA, 2010, pp. 165-172.
• [7] T. Kim, T. Attias, S.-Y. Lee, and T.-W. Lee, "Blind source separation exploiting higher-order frequency dependencies," IEEE trans. ASLP, vol. 15, no.1, pp. 70-79, 2006.
• [8] I. Lee, T. Kim, and T.-W. Lee, "Fast fixed-point independent vector analysis algorithms for convolutive blind source separation," Signal Processing, vol. 87, no. 8, pp. 1859-1871, 2007.
• [9] N. Ono, "Stable and fast update rules for independent vector analysis based on auxiliary function technique," in Proc. WASPAA, 2011, p.189-192.
• [10] N. Ono, "Auxiliary-function-based independent vector analysis with power of vector-norm type weighting functions," in Proc. APSIPA ASC, 2012, pp. 1-4.
• [11] R. Scheibler and N. Ono, "Fast and stable blind source separation with rank-1 updates," in Proc. ICASSP, 2020, pp. 236-240.
• [12] A. Brendel and W. Kellermann, "Faster IVA: Update rules for independent vector analysis based on negentropy and the majorize-minimize principle," in Proc. WASPAA, 2021, pp. 131–135.
• [13] R. Scheibler, "Independent vector analysis via log-quadratically penalized quadratic minimization," IEEE Trans. Signal Processing, vol. 69, pp. 2509-2524, 2021.
• [14] R. Ikeshita and T. Nakatani, "ISS2: An extension of iterative source steering algorithm for majorization-minimization-based independent vector analysis," in Proc. EUSIPCO, 2022, pp. 65-69.
• [15] D. Kitamura, N. Ono, H. Sawada, H. Kameoka, and H. Saruwatari, "Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization," IEEE/ACM Trans. ASLP, vol. 24, no. 9, pp. 1626-1641, 2016.
• [16] D. Kitamura, S. Mogami, Y. Mitsui, N. Takamune, H. Saruwatari, N. Ono, Y. Takahashi, and K. Kondo, "Generalized independent low-rank matrix analysis using heavy-tailed distributions for blind source separation," EURASIP J. Adv. in Signal Processing, vol. 2018, no. 28, 25 pages, 2018.
• [17] T. Nakashima, R. Scheibler, Y. Wakabayashi, and N. Ono, "Faster independent low-rank matrix analysis with pairwise updates of demixing vectors," in Proc. EUSIPCO, 2021, pp. 301-305.
• [18] Y. Mitsui, D. Kitamura, N. Takamune, H. Saruwatari, Y. Takahashi, K. Kondo, "Independent low-rank matrix analysis based on parametric majorization-equalization algorithm", in Proc. CAMSAP, 2017, pp. 98-102.
• [19] R. Ikeshita, "Independent positive semidefinite tensor analysis in blind source separation," in Proc. EUSIPCO, 2018, pp. 1652-1656.
• [20] T. Kondo, K. Fukushige, N. Takamune, D. Kitamura, H. Saruwatari, R. Ikeshita, and T. Nakatani, "Convergence-guaranteed independent positive semidefinite tensor analysis based on Student's t distribution," in Proc ICASSP, 2020, pp. 681-685.
• [21] A. Ozerov and C. Fevotte, "Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation," IEEE Trans. ASLP, vol. 18, no. 3, pp. 550-563, 2010.
• [22] H. Sawada, H. Kameoka, S. Araki, and N. Ueda, "Multichannel extensions of non-negative matrix factorization with complex-valued data," IEEE Trans. ASLP, vol. 21, no. 5, pp. 971-982, 2013.
• [23] K. Yoshii, K. Itoyama, and M. Goto, "Student's T nonnegative matrix factorization and positive semidefinite tensor factorization for single-channel audio source separation," in Proc. ICASSP, 2016, pp. 51-55.
• [24] K. Sekiguchi, A. A. Nugraha, Y. Bando, and K. Yoshii, "Fast multichannel source separation based on jointly diagonalizable spatial covariance matrices," in Proc. EUSIPCO, 2019, pp. 1-5.
• [25] K. Yatabe and D. Kitamura, "Determined blind source separation via proximal splitting algorithm," in Proc. ICASSP, 2018, pp. 776-780.
• [26] N. Ito, S. Araki, and T. Nakatani. "Complex angular central Gaussian mixture model for directional statistics in mask-based microphone array signal processing," in Proc. EUSIPCO, 2016, pp. 1153-1157.

LICENSE

Apache License 2.0