Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tky823/ssspy
A Python toolkit for sound source separation.
https://github.com/tky823/ssspy
audio-source-separation blind-source-separation ilrma ipsdta iva mnmf numpy python sound-source-separation
Last synced: 3 months ago
JSON representation
A Python toolkit for sound source separation.
- Host: GitHub
- URL: https://github.com/tky823/ssspy
- Owner: tky823
- License: apache-2.0
- Created: 2022-04-29T00:48:31.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-21T14:11:15.000Z (8 months ago)
- Last Synced: 2024-07-15T22:38:47.682Z (4 months ago)
- Topics: audio-source-separation, blind-source-separation, ilrma, ipsdta, iva, mnmf, numpy, python, sound-source-separation
- Language: Python
- Homepage: https://sound-source-separation-python.readthedocs.io/en/v0.1.7/
- Size: 10.5 MB
- Stars: 118
- Watchers: 6
- Forks: 10
- Open Issues: 23
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.rst
- License: LICENSE
Awesome Lists containing this project
README
# ssspy
[](https://sound-source-separation-python.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/tky823/ssspy/actions/workflows/test_package.yaml)
[](https://codecov.io/gh/tky823/ssspy)
[](https://tky823-ssspy-demo.hf.space/)
A Python toolkit for sound source separation.
## Installation
You can install by pip.
```shell
pip install ssspy
```
To install latest version,
```shell
pip install git+https://github.com/tky823/ssspy.git
```
Instead, you can build package from source.
```shell
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`.
```shell
pip install -e ".[docs,notebooks]"
```
You need to convert some notebooks by the following command:
```shell
# in ssspy/
. ./docs/pre_build.sh
```
When you build the documentation, run the following command.
```shell
cd docs/
make html
```
Or, you can build the documentation automatically using `sphinx-autobuild`.
```shell
# in ssspy/
sphinx-autobuild docs docs/_build/html
```
## Blind Source Separation Methods
| Method | Notebooks |
|:-:|:-:|
| Independent Component Analysis (ICA) [1-3] | Gradient-descent-based ICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ICA/GradICA.ipynb)
Natural-gradient-descent-based ICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ICA/NaturalGradICA.ipynb)
Fast ICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ICA/FastICA.ipynb) |
| Frequency-Domain Independent Component Analysis (FDICA) [4-6] | Gradient-descent-based FDICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/GradFDICA.ipynb)
Natural-gradient-descent-based FDICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/NaturalGradFDICA.ipynb)
Auxiliary-function-based FDICA (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/AuxFDICA-IP1.ipynb)
Auxiliary-function-based FDICA (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/AuxFDICA-IP2.ipynb)
Gradient-descent-based Laplace-FDICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/GradLaplaceFDICA.ipynb)
Natural-gradient-descent-based Laplace-FDICA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/NaturalGradLaplaceFDICA.ipynb)
Auxiliary-function-based Laplace-FDICA (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/AuxLaplaceFDICA-IP1.ipynb)
Auxiliary-function-based Laplace-FDICA (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/FDICA/AuxLaplaceFDICA-IP2.ipynb) |
| Independent Vector Analysis (IVA) [7-14] | Gradient-descent-based IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/GradIVA.ipynb)
Natural-gradient-descent-based IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/NaturalGradIVA.ipynb)
Fast IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/FastIVA.ipynb)
Faster IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/FasterIVA.ipynb)
Auxiliary-function-based IVA (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxIVA-IP1.ipynb)
Auxiliary-function-based IVA (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxIVA-IP2.ipynb)
Auxiliary-function-based IVA (ISS1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxIVA-ISS1.ipynb)
Auxiliary-function-based IVA (ISS2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxIVA-ISS2.ipynb)
Auxiliary-function-based IVA (IPA): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxIVA-IPA.ipynb)
Gradient-descent-based Laplace-IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/GradLaplaceIVA.ipynb)
Natural-gradient-descent-based Laplace-IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/NaturalGradLaplaceIVA.ipynb)
Auxiliary-function-based Laplace-IVA (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxLaplaceIVA-IP1.ipynb)
Auxiliary-function-based Laplace-IVA (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxLaplaceIVA-IP2.ipynb)
Auxiliary-function-based Laplace-IVA (ISS1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxLaplaceIVA-ISS1.ipynb)
Auxiliary-function-based Laplace-IVA (ISS2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxLaplaceIVA-ISS2.ipynb)
Auxiliary-function-based Laplace-IVA (IPA): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxLaplaceIVA-IPA.ipynb)
Gradient-descent-based Gauss-IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/GradGaussIVA.ipynb)
Natural-gradient-descent-based Gauss-IVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/NaturalGradGaussIVA.ipynb)
Auxiliary-function-based Gauss-IVA (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxGaussIVA-IP1.ipynb)
Auxiliary-function-based Gauss-IVA (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxGaussIVA-IP2.ipynb)
Auxiliary-function-based Gauss-IVA (ISS1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxGaussIVA-ISS1.ipynb)
Auxiliary-function-based Gauss-IVA (ISS2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxGaussIVA-ISS2.ipynb)
Auxiliary-function-based Gauss-IVA (IPA): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IVA/AuxGaussIVA-IPA.ipynb) |
| Independent Low-Rank Matrix Analysis (ILRMA) [15-18] | Gauss-ILRMA (IP1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IP1-MM.ipynb)
Gauss-ILRMA (IP1/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IP1-ME.ipynb)
Gauss-ILRMA (IP2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IP2-MM.ipynb)
Gauss-ILRMA (IP2/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IP2-ME.ipynb)
Gauss-ILRMA (ISS1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-ISS1-MM.ipynb)
Gauss-ILRMA (ISS1/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-ISS1-ME.ipynb)
Gauss-ILRMA (ISS2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-ISS2-MM.ipynb)
Gauss-ILRMA (ISS2/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-ISS2-ME.ipynb)
Gauss-ILRMA (IPA/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IPA-MM.ipynb)
Gauss-ILRMA (IPA/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GaussILRMA-IPA-ME.ipynb)
*t*-ILRMA (IP1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-IP1-MM.ipynb)
*t*-ILRMA (IP1/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-IP1-ME.ipynb)
*t*-ILRMA (IP2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-IP2-MM.ipynb)
*t*-ILRMA (IP2/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-IP2-ME.ipynb)
*t*-ILRMA (ISS1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-ISS1-MM.ipynb)
*t*-ILRMA (ISS1/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-ISS1-ME.ipynb)
*t*-ILRMA (ISS2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-ISS2-MM.ipynb)
*t*-ILRMA (ISS2/ME): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/TILRMA-ISS2-ME.ipynb)
GGD-ILRMA (IP1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GGDILRMA-IP1-MM.ipynb)
GGD-ILRMA (IP2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GGDILRMA-IP2-MM.ipynb)
GGD-ILRMA (ISS1/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GGDILRMA-ISS1-MM.ipynb)
GGD-ILRMA (ISS2/MM): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ILRMA/GGDILRMA-ISS2-MM.ipynb) |
| Independent Positive Semidefinite Tensor Analysis (IPSDTA) [19, 20] | Gauss-IPSDTA (VCD): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IPSDTA/GaussIPSDTA-VCD.ipynb)
*t*-IPSDTA (VCD): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/IPSDTA/TIPSDTA-VCD.ipynb) |
| Multichannel Nonnegative Matrix Factorization (MNMF) [21-24] | Gauss-MNMF: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/MNMF/GaussMNMF.ipynb)
*t*-MNMF: soon
Fast Gauss-MNMF (IP1): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/MNMF/FastGaussMNMF-IP1.ipynb)
Fast Gauss-MNMF (IP2): [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/MNMF/FastGaussMNMF-IP2.ipynb) |
| Blind Source Separation via Primal-Dual Splitting Algorithm (PDS-BSS) [25,26] | PDS-BSS: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/PDSBSS/PDSBSS.ipynb)
PDS-BSS-multiPenalty: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/PDSBSS/PDSBSS_multi-penalty.ipynb)
PDS-BSS-masking: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/PDSBSS/PDSBSS_masking.ipynb) |
| Blind Source Separation via Alternating Direction Method of Multipliers (ADMM-BSS) | ADMM-BSS: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/ADMMBSS/ADMMBSS.ipynb) |
| Harmonic Vector Analysis (HVA) [27] | HVA: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/HVA/HVA.ipynb) |
| Complex Angular Central Gaussian Mixture Model (cACGMM) [28] | cACGMM: [](https://colab.research.google.com/github/tky823/ssspy/blob/main/notebooks/BSS/CACGMM/CACGMM.ipynb) |
- [1] [P. Comon, "Independent component analysis, a new concept?" Signal Processing, vol. 36, no. 3, pp. 287-314, 1994.](https://www.sciencedirect.com/science/article/pii/0165168494900299)
- [2] [S. Amari, A. Cichocki, and H. H. Yang, "A new learning algorithm forblind signal separation," in *Proc. NIPS*, 1996, pp. 757-763.](https://proceedings.neurips.cc/paper/1995/hash/e19347e1c3ca0c0b97de5fb3b690855a-Abstract.html)
- [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.](https://www.cs.helsinki.fi/u/ahyvarin/papers/TNN99new.pdf)
- [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](https://www.sciencedirect.com/science/article/pii/S0925231200003453)
- [5] [H. Sawada, S. Araki, and S. Makino, "Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment," 2011.](https://ieeexplore.ieee.org/document/5473129)
- [6] [N. Ono and S. Miyabe, "Auxiliary-function-based independent componentanalysis for super-Gaussian sources," in *Proc. LVA/ICA*, 2010, pp. 165-172.](https://link.springer.com/chapter/10.1007/978-3-642-15995-4_21)
- [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.](https://link.springer.com/chapter/10.1007/11679363_21)
- [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.](https://ieeexplore.ieee.org/document/6082320)
- [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.](https://ieeexplore.ieee.org/document/6411886)
- [11] [R. Scheibler and N. Ono, "Fast and stable blind source separation with rank-1 updates," in *Proc. ICASSP*, 2020, pp. 236-240.](https://ieeexplore.ieee.org/document/9053556)
- [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.](https://arxiv.org/abs/2003.09531)
- [13] [R. Scheibler, "Independent vector analysis via log-quadratically penalized quadratic minimization," *IEEE Trans. Signal Processing*, vol. 69, pp. 2509-2524, 2021.](https://ieeexplore.ieee.org/document/9399809)
- [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.](https://arxiv.org/abs/2202.00875)
- [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.](https://ieeexplore.ieee.org/document/7486081)
- [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.](https://link.springer.com/article/10.1186/s13634-018-0549-5)
- [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.](https://ieeexplore.ieee.org/document/9287508)
- [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.](https://arxiv.org/abs/1710.01589)
- [19] [R. Ikeshita, "Independent positive semidefinite tensor analysis in blind source separation," in *Proc. EUSIPCO*, 2018, pp. 1652-1656.](https://ieeexplore.ieee.org/document/8553546)
- [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.](https://ieeexplore.ieee.org/document/9054150)
- [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.](https://ieeexplore.ieee.org/document/5229304)
- [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.](https://ieeexplore.ieee.org/document/6410389)
- [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.](https://ieeexplore.ieee.org/document/7471635)
- [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.](https://arxiv.org/abs/1903.03237)
- [25] [K. Yatabe and D. Kitamura, "Determined blind source separation via proximal splitting algorithm," in *Proc. ICASSP*, 2018, pp. 776-780.](https://ieeexplore.ieee.org/document/8462338)
- [26] [K. Yatabe and D. Kitamura, "Time-frequency-masking-based determined BSS with application to sparse IVA," in *Proc. ICASSP*, 2019, pp. 715-719.](https://ieeexplore.ieee.org/document/8682217)
- [27] [K. Yatabe and D. Kitamura, "Determined BSS based on time-frequency masking and its application to harmonic vector analysis," *IEEE/ACM Trans. ASLP*, vol. 29, pp. 1609–1625, 2021.](https://dl.acm.org/doi/abs/10.1109/TASLP.2021.3073863)
- [28] [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.](https://ieeexplore.ieee.org/document/7760429)
## LICENSE
Apache License 2.0