Skip to main content

TEST DEMO

Project description

# Speech Enhancement Evaluation Metrics

计算语音增强相关的评价指标,计算结果会被保存为 Excel 表格。

## Usage

安装依赖:

```shell
# PESQ
git clone https://github.com/vBaiCai/python-pesq.git
cd python-pesq
python setup.py install

# STOI
pip install pystoi

# tqdm
pip install tqdm

# Librosa
pip install librosa

# tablib
pip install tablib
```

使用方法:

```shell
Speech Enhancement Evaluation Metrics

optional arguments:
-h, --help
show this help message and exit
--nosiy_dir NOSIY_DIR
带噪语音目录
--denosiy_dir DENOSIY_DIR
降噪语音的目录
--clean_dir CLEAN_DIR
纯净语音的目录
--output_path OUTPUT_PATH
评价指标存储的全路径,必须以拓展名 .xls 结尾
--limit LIMIT
被测试语音的数量。默认为0,表示不限制数量
--offset OFFSET
从某个索引位置开始计算评价指标,默认为0,表示从索引为 0 的语音开始计算
--sr SR
语音文件的采样率
```

例如:

```shell
python main.py --nosiy_dir /media/imucs/DataDisk/haoxiang/Release/speech_enhancement/release_-5_0_30_50/test/noisy/ --denosiy_dir ../se_-5_0_30_50_VCC/output/ --clean_dir /media/imucs/DataDisk/haoxiang/Release/speech_enhancement/release_-5_0_30_50/test/clean
```

## ToDo

- [x] 实现测试 stoi 和 metric 的评价功能
- [x] 生成表格

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

SPEMM-1.1.9-py2.py3-none-any.whl (6.4 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file SPEMM-1.1.9-py2.py3-none-any.whl.

File metadata

  • Download URL: SPEMM-1.1.9-py2.py3-none-any.whl
  • Upload date:
  • Size: 6.4 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.4.2 requests/2.18.4 setuptools/39.1.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for SPEMM-1.1.9-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 15d1e17d5d98c0f65290f11af878322d1a31b7c013ce41bd8fe5d0057789dfb6
MD5 48724e32551907b8b3563bdd18244beb
BLAKE2b-256 e83c9c2ec9349d510de6a0f5557b57a3ea12d3fa001cf8eb80590f764243e8d7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page