yong xu @ seattle

Hi Lupeng, Yes, the code has this problem. One way is to split your data into several parts and load to the CPU memory in several times. The second way...

Hi, 这里有我的最佳模型 demo， matlab解码： https://github.com/yongxuUSTC/DNN-Speech-enhancement-demo-tool 提高PESQ: dropout，noise aware training，mask-based post-processing, etc. [1]A Regression Approach to Speech Enhancement Based on Deep Neural Networks.YongXu,JunDu,Li-Rong Dai and Chin-Hui Lee, IEEE/ACM Transactions on Audio,Speech,...

Hi, The PESQ source code was not written by me, I imported or complied from other sources. The basic usage way is: ./pesq +16000 enh.wav ref.wav ./pesq sample_rate(commonly is 16khz...

Hi , you should add "-lm": $ gcc -o PESQ *.c -lm Compile and use PESQ for speech enhancement evaluation: Download the PESQ source code from: https://www.itu.int/rec/T-REC-P.862-200102-I/en Then compile: $...

Hi, No problem at all. Thanks for your contribution. Best regards, yong On Mon, 11 Mar 2019 at 22:30, jeonghwaYoo wrote: > I created Windows version of this project (...

Hi, Yes, It is also fine for me. Best regards, yong On Wed, 16 Jan 2019 at 15:21, qiuqiangkong wrote: > Hi, many thanks! That is absolutely fine! > >...

你的hop size是一帧吗？即每次移位一帧处理，确保最大的overlap，减少不连续性。另外可以试下LSTM On Fri, 7 May 2021 at 00:29, Li leevin ***@***.***> wrote: > 您好！非常感谢你的开源代码供大家学习参考。我已经minidata上跑通了代码。现在我尝试用我自己的data > set训练网络，试过3帧输入和5帧输入，处理结果会出现明显的帧间不连续（在时域上表现为，上一帧的最后一个样本点与当前帧的第一个样本点明显不连续，在频域上表现为通频带的竖线），听起来有令人不适的噪声。请问你们是否遇到这种问题？如果遇到，你们是怎么解决的？如果没遇到，是否有些思路给我启发？非常感谢！ > 具体如图： > [image: 11] > > [image: 22] > > > —...

STFT win/hop=512/256 没问题。我上面问的是 你的DNN输入5帧的时候，这5帧每次 只移位1帧吧？跳帧可能会导致不连续。不过你用LSTM可能会好些，因为是句子级连续输入 连续预测的 On Fri, 7 May 2021 at 18:44, Li leevin ***@***.***> wrote: > 你的hop size是一帧吗？即每次移位一帧处理，确保最大的overlap，减少不连续性。另外可以试下LSTM > … > On Fri, 7 May 2021 at 00:29,...

0dB的时候 首先 任务比较难，确实 有吱吱的声音，主要是模型不够强大，带来的非线性失真 On Fri, 15 May 2020 at 19:37, lymiou wrote: > 您好，我想问下为什么增强后的语音发出来的只有吱吱吱的声音呢？ > 下面是它对应的语谱图，请问下是出了什么问题呢？期待您的解答，谢谢！ > [image: image] > > > — > You are receiving this because...

你把增强的wav和mix wav发给我听听，用mini data 训练数据是不够的，需要更大的训练数据来训练，才有比较好的结果。另外你可以试下SNR高的例子 增强看看效果，验证代码是否正确 On Fri, 23 Apr 2021 at 22:09, smylab ***@***.***> wrote: > > 您好，我是刚接触语音增强的小白，本来是打算用这份代码学习的，结果运行了好几次minidata里的数据，代码是原封不动运行的，环境也是按照要求去配置的，，，但增强后的结果除了吱吱吱吱吱吱吱吱吱吱吱，基本的混合语音都听不到了，只有吱吱吱的声音，我快疯了，，这个怎么回事，您最终怎么解决这个问题的，，万分感谢，我快被搞疯了。 > > — > You are receiving this because you commented. >...