Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

数据集相关问题 #5

Open
hulucky1102 opened this issue Dec 13, 2024 · 3 comments
Open

数据集相关问题 #5

hulucky1102 opened this issue Dec 13, 2024 · 3 comments

Comments

@hulucky1102
Copy link

作者你好,我看数据集人声目标存在200hz高通滤波,请问该数据集有没有没有进行高通滤波的原始版本

@BingYang-20
Copy link
Member

你好,数据集开源的数据未进行高通滤波。用于生成目标语音(增强标注)的设备频响是单独测量的,测量使用的扫频信号频率范围是0-24kHz,因此设备频响的频率范围也是0-24kHz,未涉及200hz高通滤波。

@hulucky1102
Copy link
Author

感谢回复,训练出来的模型对0-200hz的人声保留程度不是很好,我抽取部分数据(训练、验证)看0-200hz的人声数据都是存在缺失的,以为数据集进行了预处理。

@BingYang-20
Copy link
Member

BingYang-20 commented Dec 26, 2024

一般,说话人基频(女性普遍高于男性)以下的频率声学成分较弱,可能抽取数据的说话人基频在0-200Hz之内,所以小于基频会存在人声‘’缺失‘’,可以关注一下听感上是否出现异常。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants