xiaoqi91
xiaoqi91
您好,我下载了最新的代码,用python3.9运行报了下面的错误:TypeError: in method 'EchoCanceller_process', argument 2 of type 'std::string const &'。我看之前也有人遇到了同样的错误,现在代码仍然不兼容python3?
I use denoise.c to extract features. And I changed count to 100000, so it printed 100000*75 on the screen. However when I run bin2hdf5.py , an error occurs: "cannot reshape...
Thanks for sharing your excellent work! How long is the delay (look ahead) in ms of the normal sudo_rm_rf model? thank you.
作者好,在论文Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers中提出了三种online SpatialNet, 有两个问题请教: 1. 三种类型的online SpatialNet 的look ahead(将来帧)长度都是0吗? 2. 三种类型的online SpatialNet用到的历史帧长度分别是多少? 谢谢您
您好,在论文“Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers”中提出了在线版本的SpatialNet,但是论文中的实验都是语音增强任务(没有分离),请问是否测试过online SpatialNet语音分离的效果以及联合的增强和分离效果?主要想了解在线版本的SpatialNet相比离线版本,做speech separation/联合分离增强性能会不会下降很多?谢谢您,期待回复