ewan-xu / aec3 Goto Github PK
View Code? Open in Web Editor NEWAEC3 Extracted From WebRTC
AEC3 Extracted From WebRTC
該如何將這個專案編譯成可匯入到android專案中的library?
Hi,
I am not much familiar with the C projects but I had to select this project as I am working on this area. I tried to build this project with Visual Studio 2022 and ran into a bunch of errors. Can you please show a little detailed path to how can I build and run this.? should I must use Visual Studi 2015? and then should set any extra settings before running? Thanks.
近端录音是很干净的声音,远端有人说话,通过这个算法后,近端处理后的声音有小回声,AEC3算法本身的问题吗
AEC3用的是 kalman + PBFDAK 的双滤波器形式,我用AEC3跑了很多的音频之后发现:它在双工部分有较多的残留回声,更多的还是靠NLP来压。这样不就完全没有体现到kalman滤波器的优势吗?kalman滤波器在双工的时候表现应该远比这好才对。总的来说,它的双工性能似乎不好,是它在计算上的精简导致的吗?
作者你好,感谢你的开源代码,请问有没有基于APM实现的aec3的例子或者相关的资料
你好!我下载了你裁剪出来的AEC3的代码,有个疑问:audio_processing/audio_buffer.cc 这个文件中,void AudioBuffer::SplitIntoFrequencyBands() 函数中的 "if (num_bands_ > 1) {...}" 这个判断条件,是你自己加上去的,还是在某一版本的WebRTC的源码中就已经存在呢?谢谢!
如题
hi,我看了你在 CSDN 的文章,其中写到:“通过与kalman滤波器仔细对比可以发现,其实这个滤波器是kalman滤波器的精简版,其更新公式与kalman滤波器是一样的,只不过精简了系数误差协方差的计算,计算的是滤波器抽头系数误差协方差的平均,而不是计算每块滤波器抽头系数的误差协方差”。
我想知道这个“滤波器抽头系数误差协方差”指的是 Erl(t) = sum{H(n)*H(n)} 还是 E2(t) 呢(因为mu的更新公式中出现了 N * E2,我猜可能就是块平均)?
我对C++工程不是很熟,找了挺久没有找到对应的精简计算在哪里,可以帮我解释一下或者贴出来精简部分的代码在哪里吗
我愿称之为好活!
I see that you're using visual studio. But I know that AEC3 is cross platform. Do you think there's many changes necessary to get it working on Mac ?
Could you please add a link to my Qt adaptation?
It uses Cmake and can be very useful for who wants a realtime example with microphone and speakers
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.