0three / Speech-Denoise-With-Feature-Loss
本项目使用中文人声的数据集,在Speech Denoising with Deep Feature Losses网络的基础上fine-tune,得到对中文音频有更好去噪效果的结果
☆26Updated 4 years ago
Related projects: ⓘ
- 以音素建模构建NN-CTC声学模型☆15Updated 5 years ago
- 语音处理,声源定位中的一些基本特征☆46Updated 6 years ago
- 采用端到端方法构建声学模型,以字为建模单元,采用DCNN-CTC网络结构。☆71Updated 5 years ago
- ☆63Updated this week
- 语音降噪☆23Updated 6 years ago
- Matlab implementation of the paper Noise Spectrum Estimation in Adverse Environments: Improved Minima Controlled Recursive Averaging☆69Updated 7 years ago
- DNN and RCED speech enhancement☆19Updated 7 months ago
- 利用webRTC对语音进行处理,实现VAD和降噪处理☆48Updated 5 years ago
- Use ctc to do chinese speech recognition by keras / 通过keras和ctc实现中文语音识别☆43Updated 6 years ago
- 语音信号处理的基本知识☆32Updated 5 years ago
- ☆21Updated this week
- Full implementation of "End-to-end microphone permutation and number invariant multi-channel speech separation" (Interspeech 2020)☆55Updated 3 years ago
- 基于深度学习的语音增强、去混响☆85Updated 7 months ago
- ☆26Updated this week
- The updated version of TDAA model.☆14Updated 4 years ago
- Automatic Speech Recognition with TensorFlow(CNN+BLSTM+CTC)☆12Updated 6 years ago
- 用于机器学习的语音特征提取,包含FBank和MFCC等,原理讲解和step by step的实现☆48Updated 5 years ago
- ☆30Updated this week
- ☆29Updated this week
- Listen, Attend and Spell - PyTorch Implementation☆17Updated 5 years ago
- about Speech enhancement☆33Updated 6 years ago
- Keras implementation of speech enhancement based on LSGAN☆20Updated 6 years ago
- A neural network consist of cnn and lstm for speech enhancement☆24Updated 6 years ago
- SpEx+(tied) source code☆72Updated last year
- PyTorch implementation of "Jointly Adversarial Enhancement Training for Robust End-to-End Speech Recognition"☆19Updated 5 years ago
- 为音频 加混响的代码☆25Updated last year
- 语音识别 语音前端处理 语音合成 语音转换等等语音技术的资料汇总☆22Updated 4 years ago
- This is a implementation of kaldi-plda.☆15Updated 6 years ago
- Noise15 , Noisex-92 and Nonspeech☆29Updated 3 years ago
- Region proposal network based small-footprint keyword spotting (Pytorch)☆51Updated 10 months ago