| Name | voice-toolbox JSON |
| Version |
1.0.0
JSON |
| download |
| home_page | None |
| Summary | Convenient wrappers for audio signal processing in Python |
| upload_time | 2024-04-26 15:37:03 |
| maintainer | None |
| docs_url | None |
| author | Emma Hughson |
| requires_python | >=3.5 |
| license | None |
| keywords |
audio
audio analysis
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Voice Toolbox <img align="left" width="90" height="90" src="soundwave.jpeg">
The place to solve all your audio signal processing needs.
The current repo is under **construction**. Goal is to create a repository that contains all voice signal processing functions available from different open source projects and libraries, such as parsel mouth and librosa.
## Files
**To start**: Setup a conda environment and run 'pip3 install -r requirements.txt' before running the available scripts.
>> **Important**: if you get an error with parselmouth make sure the installation is 'pip3 install praat-parselmouth'
________________________________________________________________________________________________________________________
The script for extracting features is parsel_process.py.
* **To run**: "python3 feature_extraction.py [sampling rate] [filepath] [output filepath] --[feature flag]"
> **feature flags**: formants, ZCR, harmonics, rate_of_speech, loudness, pitch_features, spectral_features, energy
### **Features currently availabe**:
1. *Spectral Features*:
* pitch
* pitch range
* spectral slope
* mel-frequency cepstral coefficients (MFCC)
* mean spectral roll-off
* median F0 (fundamental frequency)
2. *Rate of Speech* and *loudness*:
* max intensity
* mean intensity
* syllables per second
* pause rate
* energy
3. *Harmonics*
* harmonics to noise (HNR)
* Formants: f1,f2, f3, f4
* number of zero crossings (ZCR)
### Extra Scripts for processed features
For visualization:
1. visualize_voice.py for all scatter plots along with other plotting features from praat.
* To run: 'python3 visualize_voice.py'
2. radar_plot.py for all radar plots
* To run: 'python3 radar_plot.py'
For PCA analysis of voice data:
voice_pca.py is for PCA, RFE and Correlation plot:
* - To run: 'voice_pca.py'
________________________________________________________________________________________________________________________
Raw data
{
"_id": null,
"home_page": null,
"name": "voice-toolbox",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.5",
"maintainer_email": null,
"keywords": "audio, audio analysis",
"author": "Emma Hughson",
"author_email": "Paige Tuttosi <ptuttosi@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/43/a4/07965a1e06f197c857ce1a3ffc3cfee8d2371367bc71b4adb8500db965b5/voice_toolbox-1.0.0.tar.gz",
"platform": null,
"description": "# Voice Toolbox <img align=\"left\" width=\"90\" height=\"90\" src=\"soundwave.jpeg\">\r\nThe place to solve all your audio signal processing needs. \r\n\r\nThe current repo is under **construction**. Goal is to create a repository that contains all voice signal processing functions available from different open source projects and libraries, such as parsel mouth and librosa. \r\n\r\n## Files\r\n**To start**: Setup a conda environment and run 'pip3 install -r requirements.txt' before running the available scripts. \r\n>> **Important**: if you get an error with parselmouth make sure the installation is 'pip3 install praat-parselmouth'\r\n\r\n________________________________________________________________________________________________________________________\r\nThe script for extracting features is parsel_process.py. \r\n * **To run**: \"python3 feature_extraction.py [sampling rate] [filepath] [output filepath] --[feature flag]\"\r\n \r\n > **feature flags**: formants, ZCR, harmonics, rate_of_speech, loudness, pitch_features, spectral_features, energy\r\n\r\n### **Features currently availabe**:\r\n1. *Spectral Features*:\r\n* pitch\r\n* pitch range\r\n* spectral slope\r\n* mel-frequency cepstral coefficients (MFCC)\r\n* mean spectral roll-off\r\n* median F0 (fundamental frequency)\r\n\r\n2. *Rate of Speech* and *loudness*:\r\n* max intensity\r\n* mean intensity\r\n* syllables per second\r\n* pause rate\r\n* energy\r\n\r\n3. *Harmonics*\r\n* harmonics to noise (HNR)\r\n* Formants: f1,f2, f3, f4\r\n* number of zero crossings (ZCR)\r\n\r\n### Extra Scripts for processed features\r\nFor visualization:\r\n 1. visualize_voice.py for all scatter plots along with other plotting features from praat. \r\n * To run: 'python3 visualize_voice.py'\r\n 2. radar_plot.py for all radar plots\r\n * To run: 'python3 radar_plot.py'\r\n\r\nFor PCA analysis of voice data:\r\n voice_pca.py is for PCA, RFE and Correlation plot:\r\n* - To run: 'voice_pca.py'\r\n\r\n________________________________________________________________________________________________________________________\r\n\r\n\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Convenient wrappers for audio signal processing in Python",
"version": "1.0.0",
"project_urls": null,
"split_keywords": [
"audio",
" audio analysis"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "42a69e1cf8cc454d4c40359865057739cd8490ec0dde22260ba6964191079288",
"md5": "1d896fd13e248bcc66e8bf6dc68f0c60",
"sha256": "78bd431dfc6ff815cde486dbdfee404bd73c94eaa5d5527995d58eb46afdd134"
},
"downloads": -1,
"filename": "voice_toolbox-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1d896fd13e248bcc66e8bf6dc68f0c60",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.5",
"size": 8637,
"upload_time": "2024-04-26T15:37:01",
"upload_time_iso_8601": "2024-04-26T15:37:01.577079Z",
"url": "https://files.pythonhosted.org/packages/42/a6/9e1cf8cc454d4c40359865057739cd8490ec0dde22260ba6964191079288/voice_toolbox-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "43a407965a1e06f197c857ce1a3ffc3cfee8d2371367bc71b4adb8500db965b5",
"md5": "5a4ccc1a64a1bc25aaf0b455e5a85816",
"sha256": "4ffabb7357fe6d2b34337cff28024b48b60c8ba0be68c6958ea8a476c2d21f79"
},
"downloads": -1,
"filename": "voice_toolbox-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "5a4ccc1a64a1bc25aaf0b455e5a85816",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.5",
"size": 8860,
"upload_time": "2024-04-26T15:37:03",
"upload_time_iso_8601": "2024-04-26T15:37:03.674582Z",
"url": "https://files.pythonhosted.org/packages/43/a4/07965a1e06f197c857ce1a3ffc3cfee8d2371367bc71b4adb8500db965b5/voice_toolbox-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-26 15:37:03",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "voice-toolbox"
}
