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

音频连接处有哒哒的声音或者消音的情况 #6

Open
SongJinXue opened this issue Sep 15, 2020 · 3 comments
Open

音频连接处有哒哒的声音或者消音的情况 #6

SongJinXue opened this issue Sep 15, 2020 · 3 comments

Comments

@SongJinXue
Copy link

你号,音频分成4秒每段进行语音增强后,在音频的连接处有哒哒的声音或者会出现消音的情况,将4s改成1s后的效果更加严重,这种情况可以采用什么方式去除呢?产生的原因是因为音频不连续吗?

@huyanxin
Copy link
Owner

请问你这边数据用的是什么呢?如果你把4s每段去除,即把

decode_do_segement=True
置成false后会是什么情况呢?最好能发下样例我听听看吧。正常来说不应该出现这种情况才对,本身分段也是做了overlap来保证前后段之间的连续性,按理说不应该出现这种情况才对,样例你发我邮箱[email protected]

@SongJinXue
Copy link
Author

请问你这边数据用的是什么呢?如果你把4s每段去除,即把

decode_do_segement=True

置成false后会是什么情况呢?最好能发下样例我听听看吧。正常来说不应该出现这种情况才对,本身分段也是做了overlap来保证前后段之间的连续性,按理说不应该出现这种情况才对,样例你发我邮箱[email protected]

将decode_do_segement = flase 效果会好一点,但音频有时候会出现消音的问题,样例已发送到邮箱

@iver56
Copy link

iver56 commented Sep 30, 2020

Cross-fading segments instead of hard-cutting them can alleviate discontinuities. See illustration below.

Hard-cut:
bilde

Cross-fade:
bilde

Note: This crudely illustrates the concept. Do not actually use the illustrated curve for cross-fading. Rather use equal-power cross fading, maybe sqrt.

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

3 participants