phm-feature
介绍
使用torch torchaudio 构建PHM特征抽取功能层
功能层介绍
torchphm.layers 将phm固定使用的数据操作,固化为如下层:
- STFT 离散傅立叶变换
- Spectrogram 谱图
- MelFilterbank mel譜过滤
- AmplitudeToDb 幅度取分贝
- TimeStretch 变速不变调
- ComplexNorm 复数输出取模'范数'
- ApplyFilterbank 过滤器应用
应用场景
组合上述功能层,实现不同场景:
-
STFT 分帧==>加窗==>短时离散傅立叶变换
-
"变速不变调" Time scale modification 详细见 https://zhuanlan.zhihu.com/p/337193578 用于声谱图压缩、扩张处理,供后续分析
-
梅尔mel谱转换 对于语谱图进行mel谱转换
-
HPSS 中值滤波,过滤出频率的谐波分量与冲击分量 为什么中值滤波,可以过滤出"数据轮廓"及发现"谐波分量和冲击分量",参见 https://blog.csdn.net/qq_38131594/article/details/80758567
软件架构
软件结构说明
.
├── dist
│ ├── torchphm-1.1.7.tar.gz
│ └── torchphm-1.1.8.tar.gz
├── draw
│ ├── draw_functional.py
│ ├── draw_layers.py
│ ├── draw_torchphm_layers.ipynb
│ ├── torchphm -> ../torchphm
│ └── Untitled.ipynb
├── examples_torchphm.ipynb
├── README.md
├── setup.cfg
├── setup.py
├── tests
│ ├── test_functional.py
│ └── test_layers.py
├── torchphm
│ ├── beta_hpss.py
│ ├── functional.py
│ ├── __init__.py
│ ├── layers.py
└── torchphm.egg-info
├── PKG-INFO
dist pypi上传包 draw 画图 examples_torchphm.ipynb 应用例程 tests 测试文件 torchphm 实现源码
安装教程
使用pip进行安装
#### 参与贡献
#### 特技
Metadata
Release files for torchphm 1.1.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| torchphm-1.1.9.tar.gz | 11.9 kB | Without provenance | Details |
Release files / torchphm-1.1.9.tar.gz
| Download URL | torchphm-1.1.9.tar.gz |
|---|---|
| Size | 11.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c3cc2eebed823ee7e2d4e22bd9c11c0e6fd02b173b2950f76fb97ddf2dafddef
|
|
BLAKE2b-256 checksum How to use checksums |
2cc4143a417c00cf3a4ee266bb27dd37d8f46b301a732dab5c6f9796182846be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.8.10
|
Security for torchphm 1.1.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.