NBSS

NBSS copied to clipboard

dataset

18

Where can I find the WSJ0 dataset to run the project? Can I use other datasets instead of WSJO ?

PriyankaPaud

学长 请问下面的论文 查看的顺序是怎么样的呢?

2

学长 请问下面的论文 查看的顺序是怎么样的呢?

wrz1999

多通道数据集的生成

4

学长您好，请问有用WSJ0生成多通道的脚本嘛？不太清楚这部分要怎么做，在generate_rirs生成房间脉冲响应后，data_loaders里面的代码就不太能对应上了

dengyx99

number of speakers is unknown

1

Can NBSS be applied to scenarios where the number of speakers is unknown

abnera1

如何生成训练数据？

24

请问一下，我目前只有LDC93S6A这个数据集，在运行 sms_wsj 的make时总是出错，所以只生成了wsj_8k_zeromean(里面是wav文件)和wsj_8k_zermean.json（这文件里的性别，转录文本都是空的，我的kaldi跑不通）这两个文件，我的最终目标是把这个模型应用到2mic的阵列上，进行降噪。我要如何才能跑通这个例子呀？是不是只需要有干净数据就行了？有没有一步一步的操作步骤呀？

haha010508

Can I use shorter training and testing utterances?

1

I notice that both training and testing utterances are 4seconds long and the inference is "the evaluation utterances are first chunked to 4-second segments and processed by the network, with...

youyou098888

`state` and `share_qk` options

1

Hi again, * Is the `state` argument of the different `foward` methods always `None` in your experiments? If not, when should it be set to something different from `None`? *...

philgzl

will you combine it with speaker embedding?

2

many target speaker extraction is for single channel, multi-channel target speaker extraction is less researched. and many target speaker extraction network is time domain and performance is poor under real...

wendongj

How to train SpatialNet using CHiME3/4 dataset

1

Hi. I'm interested in SpatialNet and thank you for providing the code. I would like to implement the results from the SpatialNet paper using the CHiME3/4 dataset (Table X). However,...

CSeIn

1 有流式推理的代码不？ 2 模型转onnx格式，encoder ，self-attention和decoder 需要拆成3部分吗？是否可以出个pytorch模型转onnx的脚本，另外推理部分支持下流式。

zhixingheyixsh