Maui is a multi-purpose automatic topic indexing algorithm. Given a document, Maui automatically identifies its topics. Depending on the task topics are tags, keywords, keyphrases, vocabulary terms, descriptors or Wikipedia titles.
An experimental unsupervised learning method for improvising jazz melodies, based on restricted Boltzmann machines (RBMs) layered into Deep Belief Networks (forms of neural networks).
openEAR is the Munich Open-Source Emotion and Affect Recognition Toolkit developed at the Technische Universität München (TUM). It provides efficient (audio) feature extraction algorithms implemented in C++, classfiers, and pre-trained models on well-known emotion databases. It is now maintained and supported by audEERING. Updates will follow soon.
Secure File Transfer for Windows with Cerberus by Redwood
Protect and share files over FTP/S, SFTP, HTTPS and SCP with the #1 rated Windows file transfer server.
Cerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
This small python script will generate mp3 and corresponding text files
for learning / training the morse code. It follows the method of Koch for
teaching the characters and the method described in N0HFFs book for improving
the skills even more.
tracker interface for csound. working sco editor, drum machine exc, support for vst and csound instruments. Csound routines is also available by itself currently only for python newest version at http://pypi.python.org/simple/Dex%20Tracker/
A tool for segmenting objects of interest in images, namely creating masks, and storing them for a set of images. It may provide some automatic/interactive segmentation for certain classes of objects. For computer vision / machinelearning applications.
A database driven touchscreen digital media jukebox. Allows you to use an old machine and a touchscreen to interface to a music collection. I started this project in order to better learn Python and Qt but might move it to Python and HTML for more speed.
Software to fit whole-sentence language models using the principle of maximum entropy. For developers of speech recognizers, text prediction interfaces, OCR, machine translation software.
Amphion is an audio server and a collection of clients designed to play audio tracks, maintain playlists, and tweak the output volume. Amphion lets you plug a server into your stereo and control the tracks played on your stereo from another machine.
A collection of open source software and documents on machine perception and machinelearning. Includes a state of the art face detector (MPISearch), video labeling tools (Score), and tutorials (Kolmogorov Tutorials).