Huer
Huer
Hello, I have the same problem as you. How do you solve it?
targets = tf.concat(0,[tf.reshape(speech_f[i][self.N_IN - 1][0:self.NEFF],[1, self.NEFF]) for i in range(0, self.batch_size, 1)]) There is a problem with this part of the code (senn.py) ----ValueError: Shapes (20, 1, 129) and ()...
I have modified this part of the code targets = tf.concat(0,[tf.reshape(speech_f[i][self.N_IN - 1][0:self.NEFF],[1, self.NEFF]) for i in range(0, self.batch_size, 1)])------------------------> targets = tf.concat([tf.reshape(speech_f[i][self.N_IN - 1][0:self.NEFF],[1, self.NEFF]) for i in range(0,...
这个代码,我用过,你按照作者说明做好实验,能跑通,效果建议你看其他项目,毕竟这个挺早了
老师你好,还有一些问题需要您的帮助 1)之前的问题我修改了addnoise文件,生成了RawData数据,您可不可以帮忙看看修改效果跟您的一样吗?(尽管都是生成了带噪信号) function [ signalmix, noise ] = addnoise( signal, noise, snr ) signal = signal(:); signal=signal-mean(signal); noise = noise(:); noise=noise-mean(noise); S = length( signal ); N = length( noise...
我出现的问题和你的一致,您是如何解决的呢?
Process finished with exit code -1073741571 (0xC00000FD) 我用的pycharm,VS安装的是2015,上面是报错信息,是不是在windows下无法进行测试呢?
你好,问下这个noisy路径下的文件和clean路径下的文件是一一对应的吗? 比如: mix/a.wav clean/a.wav? mix和clean路径下的数量是一致的吗?
是不是按照徐勇老师那个代码合成的noisy呢? 多个mix对应一个clean?