Robin Scheibler
Robin Scheibler
Added both standard and optiboot bootloaders for 8MHz boards using the internal oscillator. The optiboot makefile was modified to compile the 8MHz optiboot bootloader. The upload speed had to be...
This PR adds a bunch of layers to do Blind Source Separation using Independent vector analysis, possibly with a DNN mask model. This is done in `espnet2`. I have also...
Hi FakuFaku, Is there a way to extract the 3D pseudo-spectrum data from a DOA object in the case of a 3D DOA simulation as mentioned above? Or, stated another...
I have started work for the source directivity of the ray tracer. The idea is to implement the drectivity as a random sampling of the rays on the sphere from...
I added support for the [LOCATA challenge](http://www.locata-challenge.org) dataset. This is a dataset of real recordings where the goal is to locate static and moving sources using a few different microphone...
This PR moves the code that was originally cython code to efficiently build RIR from the image sources to the C++ code base. This has two advantages. 1. Reduces complexity...
This would be useful to create anechoic simulations with properly simulated delays between microphones. There isn't much work required to get there. It is already possible to achieve this result...
The goal of the PR is to implement tools to read (and write, at a later time) rooms and files from file. The first reader implemented is simply based on...
Currently, beamformers are a sub-class of microphone array objects. Ideally, the beamformers should have a structure more similar to the DOA or adaptive filters objects. They could be a subclass...
The simulator requires the room to be completely closed. This is due to a visibility check for the image sources. Microphones outside the room are not visible and the inside/outside...