[[Paper]](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0205943)
[[Documentation]](https://neuro-team-femto.github.io/cleese)
[[Tutorials]](https://neuro-team-femto.github.io/cleese/tutorials/speech/)
CLEESE ("Ministry of Silly Talks") is a Python toolbox to help the generation of randomized sound and image stimuli for neuroscience research. It was originally created to generate arbitrary many random variations around an original speech recording (hence, "silly talks"). It has now been extended to provide a variety of sound and image transformation algorithms (so-called Engines) also able e.g. to create random expressive variations on a human face.
# Setup
You can download and install the latest version of CLEESE with the following
command:
```Bash
pip install cleese-stim
```
# Available Engines
CLEESE is currently composed of two transformation engines: `PhaseVocoder` and
`FaceWarp`.
* `PhaseVocoder` allows one to create random fluctuations around an audio
file’s original contour of pitch, loudness, timbre and speed (i.e. roughly
defined, its prosody). One of its foreseen applications is the generation of
very many random voice stimuli for reverse correlation experiments.
* `FaceWarp` uses [mediapipe](https://google.github.io/mediapipe/)'s Face Mesh
API to introduce random or precomputed deformation in the expression of a
visage on an image. This engine was designed to produce batches of deformed
faces for reverse correlation experiments.
# Basic Usage
CLEESE runs in completely in Python. Python 3.8.10 was used for the most recent testing.
## PhaseVocoder
```Python
import cleese_stim as cleese
from cleese_stim.engines import PhaseVocoder
inputFile = 'path_to_input_sound.wav'
configFile = 'path_to_config_file.toml'
cleese.generate_stimuli(PhaseVocoder, inputFile, configFile)
```
The `config_file` controls the parameters of the manipulation. For more information and further functionality see the [documentation](https://neuro-team-femto.github.io/cleese).
# Acknowledgements
CLEESE was originally designed in 2018 by [Juan José Burred](https://www.jjburred.com), [Emmanuel Ponsot](https://www.stms-lab.fr/person/emmanuel-ponsot) and [Jean-Julien Aucouturier](https://www.femto-st.fr/fr/personnel-femto/jeanaucouturier) at [STMS Lab](https://www.stms-lab.fr) (IRCAM/CNRS/Sorbonne Université, Paris - France), and released on the [IRCAM Forum](https://forum.ircam.fr/) platform. As of 2021, CLEESE is now developed and maintained by the [Neuro Team](https://neuro-team-femto.github.io/) [FEMTO-ST Institute](https://www.femto-st.fr/) (CNRS/Université Bourgogne Franche-Comté) in Besançon - France.
CLEESE's development was originally funded by the [European Research Council](https://erc.europa.eu) ([CREAM](https://neuro-team-femto.github.io/cream/) 335536, 2014-2019, PI: JJ Aucouturier), and has since then received support from [Agence Nationale de la Recherche](https://anr.fr/) (ANR SEPIA, AND Sounds4Coma), [Fondation pour l'Audition](https://www.fondationpourlaudition.org) (DASHES) and [Région Bourgogne-Franche Comté](https://www.bourgognefranchecomte.fr/) (ASPECT).
If you use CLEESE in academic work, please cite it as :
```
Burred, JJ., Ponsot, E., Goupil, L., Liuni, M. & Aucouturier, JJ. (2019).
CLEESE: An open-source audio-transformation toolbox for data-driven experiments in speech and music cognition.
PLoS one, 14(4), e0205943.
```
# License
CLEESE is a free, standalone Python module, distributed under an open-source MIT Licence on the FEMTO Neuro team [github page](https://github.com/neuro-team-femto/cleese).
Raw data
{
"_id": null,
"home_page": "https://github.com/neuro-team-femto/cleese",
"name": "cleese-stim",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "sound manipulation, phase vocoder",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/40/1f/6eec74c85ab188dbc39bd1407d770ea355b8f5a81764750a790d09a52ab1/cleese_stim-2.3.4.tar.gz",
"platform": null,
"description": "\n\n[[Paper]](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0205943)\n[[Documentation]](https://neuro-team-femto.github.io/cleese)\n[[Tutorials]](https://neuro-team-femto.github.io/cleese/tutorials/speech/)\n\nCLEESE (\"Ministry of Silly Talks\") is a Python toolbox to help the generation of randomized sound and image stimuli for neuroscience research. It was originally created to generate arbitrary many random variations around an original speech recording (hence, \"silly talks\"). It has now been extended to provide a variety of sound and image transformation algorithms (so-called Engines) also able e.g. to create random expressive variations on a human face. \n\n# Setup\n\nYou can download and install the latest version of CLEESE with the following\ncommand:\n\n```Bash\npip install cleese-stim\n```\n\n# Available Engines\n\nCLEESE is currently composed of two transformation engines: `PhaseVocoder` and\n`FaceWarp`.\n* `PhaseVocoder` allows one to create random fluctuations around an audio\n file\u2019s original contour of pitch, loudness, timbre and speed (i.e. roughly\n defined, its prosody). One of its foreseen applications is the generation of\n very many random voice stimuli for reverse correlation experiments.\n* `FaceWarp` uses [mediapipe](https://google.github.io/mediapipe/)'s Face Mesh\n API to introduce random or precomputed deformation in the expression of a\n visage on an image. This engine was designed to produce batches of deformed\n faces for reverse correlation experiments.\n\n# Basic Usage\n\nCLEESE runs in completely in Python. Python 3.8.10 was used for the most recent testing.\n\n## PhaseVocoder\n```Python\nimport cleese_stim as cleese\nfrom cleese_stim.engines import PhaseVocoder\n\ninputFile = 'path_to_input_sound.wav'\nconfigFile = 'path_to_config_file.toml'\n\ncleese.generate_stimuli(PhaseVocoder, inputFile, configFile)\n```\n\nThe `config_file` controls the parameters of the manipulation. For more information and further functionality see the [documentation](https://neuro-team-femto.github.io/cleese).\n\n# Acknowledgements\n\nCLEESE was originally designed in 2018 by [Juan Jos\u00e9 Burred](https://www.jjburred.com), [Emmanuel Ponsot](https://www.stms-lab.fr/person/emmanuel-ponsot) and [Jean-Julien Aucouturier](https://www.femto-st.fr/fr/personnel-femto/jeanaucouturier) at [STMS Lab](https://www.stms-lab.fr) (IRCAM/CNRS/Sorbonne Universit\u00e9, Paris - France), and released on the [IRCAM Forum](https://forum.ircam.fr/) platform. As of 2021, CLEESE is now developed and maintained by the [Neuro Team](https://neuro-team-femto.github.io/) [FEMTO-ST Institute](https://www.femto-st.fr/) (CNRS/Universit\u00e9 Bourgogne Franche-Comt\u00e9) in Besan\u00e7on - France.\n\nCLEESE's development was originally funded by the [European Research Council](https://erc.europa.eu) ([CREAM](https://neuro-team-femto.github.io/cream/) 335536, 2014-2019, PI: JJ Aucouturier), and has since then received support from [Agence Nationale de la Recherche](https://anr.fr/) (ANR SEPIA, AND Sounds4Coma), [Fondation pour l'Audition](https://www.fondationpourlaudition.org) (DASHES) and [R\u00e9gion Bourgogne-Franche Comt\u00e9](https://www.bourgognefranchecomte.fr/) (ASPECT).\n\n\nIf you use CLEESE in academic work, please cite it as :\n\n```\nBurred, JJ., Ponsot, E., Goupil, L., Liuni, M. & Aucouturier, JJ. (2019).\nCLEESE: An open-source audio-transformation toolbox for data-driven experiments in speech and music cognition.\nPLoS one, 14(4), e0205943.\n```\n\n# License\n\nCLEESE is a free, standalone Python module, distributed under an open-source MIT Licence on the FEMTO Neuro team [github page](https://github.com/neuro-team-femto/cleese).\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Audio and visual stimuli generation tool",
"version": "2.3.4",
"project_urls": {
"Bug Tracker": "https://github.com/neuro-team-femto/cleese/issues",
"Homepage": "https://github.com/neuro-team-femto/cleese"
},
"split_keywords": [
"sound manipulation",
" phase vocoder"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9072a8da193257f6091ae1c0a5f83681ac2f1a99bc231197ba4886b184ac9372",
"md5": "e9531ae5069c1c822cb57889a5df46cd",
"sha256": "dccc9586fd208aedebde6a81f724155642ce2a76c42854c1cb4e989b44b10114"
},
"downloads": -1,
"filename": "cleese_stim-2.3.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e9531ae5069c1c822cb57889a5df46cd",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 35247,
"upload_time": "2024-07-08T04:29:21",
"upload_time_iso_8601": "2024-07-08T04:29:21.895408Z",
"url": "https://files.pythonhosted.org/packages/90/72/a8da193257f6091ae1c0a5f83681ac2f1a99bc231197ba4886b184ac9372/cleese_stim-2.3.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "401f6eec74c85ab188dbc39bd1407d770ea355b8f5a81764750a790d09a52ab1",
"md5": "873ba0e4f630d1d79286af5cbd303c4b",
"sha256": "43083dc4660493d81fb63d3c780e2d8b885f80854ecd1bb57b357aebe78c66de"
},
"downloads": -1,
"filename": "cleese_stim-2.3.4.tar.gz",
"has_sig": false,
"md5_digest": "873ba0e4f630d1d79286af5cbd303c4b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 10765399,
"upload_time": "2024-07-08T04:29:23",
"upload_time_iso_8601": "2024-07-08T04:29:23.469293Z",
"url": "https://files.pythonhosted.org/packages/40/1f/6eec74c85ab188dbc39bd1407d770ea355b8f5a81764750a790d09a52ab1/cleese_stim-2.3.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-08 04:29:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "neuro-team-femto",
"github_project": "cleese",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "cleese-stim"
}
JSON
