# auditory_models
## Description
This repository provides multiple packages to compute auditory models, including
- Short term Objective Intelligibility ([STOI](https://ieeexplore.ieee.org/abstract/document/5713237))
- Generalized Power Spectrum Model for audio quality ([GPSMq](https://ieeexplore.ieee.org/abstract/document/8708700))
## Installation
`pip install auditory_models`
## Usage
```
from auditory_models import STOI, GPSMq
import soundfile as sf
reference, fs_ref = sf.read("reference.wav")
degraded, fs_dgr = sf.read("degraded.wav")
if fs_ref != fs_dgr:
raise ValueError("Sample rates must be equal!")
stoi = STOI()
gpsmq = GPSMq(binaural=False)
stoi.process(reference, degraded, fs_ref)
gpsmq.process(reference, degraded, fs_ref)
```
## Support
Regarding issues please feel free to contact me via
<a href="mailto:max.zimmermann@tugraz.at">max.zimmermann@tugraz.at</a>
## Contributing
Any contribution is welcome.
## Authors and acknowledgment
Author: Max Zimmermann\
Credits to:
- The developers of the original Matlab implementations
- STOI: Cees Taal
- GPSMq: Thomas Biberger and Jan-Hendrik Fleßner
- Manuel Pariente for the original Python implementation of STOI
## License
This project is licensed under the GNU General Public License v3 (GPLv3). For further info see file `COPYING`.
Raw data
{
"_id": null,
"home_page": null,
"name": "auditory-models",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "audio, quality, speech, perception, intelligibility, model, auditory, stoi, gpsm, snr",
"author": null,
"author_email": "Max Zimmermann <max.zimmermann@tugraz.at>",
"download_url": "https://files.pythonhosted.org/packages/a0/b8/a98ad54856690abccafff93984cfb9f2a6d926692fe83bc8ea47fd597586/auditory_models-0.1.1.tar.gz",
"platform": null,
"description": "# auditory_models\r\n\r\n## Description\r\n\r\nThis repository provides multiple packages to compute auditory models, including\r\n- Short term Objective Intelligibility ([STOI](https://ieeexplore.ieee.org/abstract/document/5713237))\r\n- Generalized Power Spectrum Model for audio quality ([GPSMq](https://ieeexplore.ieee.org/abstract/document/8708700))\r\n\r\n\r\n## Installation\r\n`pip install auditory_models`\r\n\r\n## Usage\r\n```\r\nfrom auditory_models import STOI, GPSMq\r\nimport soundfile as sf\r\n\r\nreference, fs_ref = sf.read(\"reference.wav\")\r\ndegraded, fs_dgr = sf.read(\"degraded.wav\")\r\nif fs_ref != fs_dgr:\r\n raise ValueError(\"Sample rates must be equal!\")\r\n\r\nstoi = STOI()\r\ngpsmq = GPSMq(binaural=False)\r\n\r\nstoi.process(reference, degraded, fs_ref)\r\ngpsmq.process(reference, degraded, fs_ref)\r\n\r\n```\r\n\r\n## Support\r\nRegarding issues please feel free to contact me via \r\n<a href=\"mailto:max.zimmermann@tugraz.at\">max.zimmermann@tugraz.at</a>\r\n\r\n## Contributing\r\nAny contribution is welcome. \r\n\r\n## Authors and acknowledgment\r\nAuthor: Max Zimmermann\\\r\nCredits to: \r\n- The developers of the original Matlab implementations\r\n - STOI: Cees Taal \r\n - GPSMq: Thomas Biberger and Jan-Hendrik Fle\u00dfner\r\n- Manuel Pariente for the original Python implementation of STOI\r\n\r\n## License\r\nThis project is licensed under the GNU General Public License v3 (GPLv3). For further info see file `COPYING`.\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Computation of auditory models",
"version": "0.1.1",
"project_urls": {
"Repository": "https://gitlab.tugraz.at/BA9D3CA475A1A669/auditory_models.git"
},
"split_keywords": [
"audio",
" quality",
" speech",
" perception",
" intelligibility",
" model",
" auditory",
" stoi",
" gpsm",
" snr"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "c946448648e756eca078ea93f363a142aac81ea9964122cdcd7fd39e69c4ccfa",
"md5": "37ba1bd31eb75d9c4f335477222e6d79",
"sha256": "c8dfa04a015726df132ea43164c90e3e7ff9505979d2f3c3ec70b3a8bf3758ed"
},
"downloads": -1,
"filename": "auditory_models-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "37ba1bd31eb75d9c4f335477222e6d79",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 31997,
"upload_time": "2025-08-27T12:33:10",
"upload_time_iso_8601": "2025-08-27T12:33:10.573739Z",
"url": "https://files.pythonhosted.org/packages/c9/46/448648e756eca078ea93f363a142aac81ea9964122cdcd7fd39e69c4ccfa/auditory_models-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "a0b8a98ad54856690abccafff93984cfb9f2a6d926692fe83bc8ea47fd597586",
"md5": "0202a067380d4a3775e2945631e4359f",
"sha256": "b2e5a5a68a623206e1abc04213b4252effaa884533f82c68cb9909ce05dd3490"
},
"downloads": -1,
"filename": "auditory_models-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "0202a067380d4a3775e2945631e4359f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 27530,
"upload_time": "2025-08-27T12:33:11",
"upload_time_iso_8601": "2025-08-27T12:33:11.809206Z",
"url": "https://files.pythonhosted.org/packages/a0/b8/a98ad54856690abccafff93984cfb9f2a6d926692fe83bc8ea47fd597586/auditory_models-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-27 12:33:11",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "auditory-models"
}
JSON