andreas12345 / cdr-dereverb Goto Github PK
View Code? Open in Web Editor NEWCoherence-based Dereverberation for Speech Enhancement
License: BSD 2-Clause "Simplified" License
Coherence-based Dereverberation for Speech Enhancement
License: BSD 2-Clause "Simplified" License
Dear Andreas
According to the paper Coherent-to-Diffuse Power Ratio Estimation for Dereverberation in the Fig. 10 in these CDR estimators the dereverberation does not work the same for low frequencies than for high frequencies. Apparently, for low frequencies the dereverberation is less. I wonder if we reduce the distance of the microphones let's say to 0.5 cm or 1 cm, our diffuse coherence model will be different, will we find the same effect for low frequencies and therefore our CDR estimator dereverberation performance will be less?
Hoping I have written properly this question.
Thanks
David
Thank you for the great work, I would just like to ask about the function of [p=IterLSDesign(cfg.Lp,cfg.K,cfg.N);] it is not available in the code, and I wonder how you get the value of p?. Also, do I need to calculate this p value if I will use a different wave file?. Is it ok to use the p value that you're using in the code to run other audio wave files?
Dear Andreas,
Thanks for your works, it does help me a lot for dereverberation and CDR.
I have two questions about CDR and your paper.
The noise coherence estimation from your paper is fixed, which is an ideal case. But in reality, the noise coherence will change along with different environments I believe, are there any other methodologies for improving that?
The paper for estimating CDR is only for 2-microphones. If I want to do multi-channels such as 8mics, do you have better way in maths to compute multi-channels(>2mics) CDR
Regards
Yongyu
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.