语言: "en" 缩略图: 标签:

• 音频到音频
• 语音增强
• WHAMR!
• SepFormer
• Transformer
• pytorch
• speechbrain 许可证: "apache-2.0" 指标:
• SI-SNR
• PESQ

基于WHAMR!训练的SepFormer语音增强模型（8kHz采样频率）

本仓库提供所有必要工具，用于通过SepFormer模型进行语音增强（去噪+去混响），该模型由SpeechBrain实现，并在WHAMR!数据集（8kHz采样频率版本，本质上是添加环境噪声和混响的WSJ0-Mix数据集）上预训练。建议访问SpeechBrain官网获取更佳体验。该模型在WHAMR!测试集上的性能为10.59 dB SI-SNR。

安装SpeechBrain

首先执行以下命令安装：

pip install speechbrain

建议阅读官方教程深入了解SpeechBrain。

对自定义音频文件增强

from speechbrain.inference.separation import SepformerSeparation as separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-whamr-enhancement", savedir='pretrained_models/sepformer-whamr-enhancement')

# 处理自定义文件时修改路径
est_sources = model.separate_file(path='speechbrain/sepformer-whamr-enhancement/example_whamr.wav') 

torchaudio.save("enhanced_whamr.wav", est_sources[:, :, 0].detach().cpu(), 8000)

GPU推理

调用from_hparams方法时添加run_opts={"device":"cuda"}参数启用GPU加速。

训练

训练脚本正在开发中，相关PR合并后将更新模型卡片。当前训练结果（模型/日志等）可在此查看。

限制说明

SpeechBrain团队不对该模型在其他数据集上的表现提供任何保证。

引用SpeechBrain

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

引用SepFormer

@inproceedings{subakan2021attention,
      title={Attention is All You Need in Speech Separation}, 
      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
      year={2021},
      booktitle={ICASSP 2021}
}

关于SpeechBrain

• 官网: https://speechbrain.github.io/
• 代码库: https://github.com/speechbrain/speechbrain/
• HuggingFace: https://huggingface.co/speechbrain/