Texmex Software¶
TEXMEX Research Team
- Efficient Exploitation of Multimedia Documents
- Exploration, Indexing, Navigation, and Access to Very Large Databases
Texmex is a joint team between the INRIA research center of Rennes - Bretagne - Atlantique and the joint research unit 6074 IRISA. The team gathers people from INRIA, CNRS, university of Rennes 1 and INSA of Rennes (an engineer school). It also hosts three associate professors from university of Rennes 2.
Website : http://www.irisa.fr/texmex/
Note
For informations and licence, please contact sebastien.campion@inria.fr
Machine Learning¶
BonzaiBoost¶
It’s a general purpose machine-learning program based on decision tree and boosting for building a classifier from text and/or attribute-value data.
GPUKmeans¶
Kmeans algorithm implementation on NVidia GPU using CuBlas.
Audio¶
AudioSeg¶
AudioSeg is a toolkit dedicated to audio segmentation and classification of audio streams. The toolkit implements standard reference algorithms such as energy-based silence detection, BIC segmentation and clustering as well as GMM/HMM classification.
The deposit of this software at APP is currently being processed.
Samusa : Speech And Music Segmenter and Annotator¶
Samusa enable to detect audio and musical segment in an multimedia content (audio,video)
The deposit of this software at APP is currently being processed.
Sirocco¶
Large vocabulary speech recognition system based on continuous density Hidden Markov Models
The deposit of this software at APP is currently being processed.
Irene : speech transcription platform¶
Irene is an automatic speech transcription platform, designed * Provide a reliable transcription (or other related extracted data) from any speech carrying file. * Give researchers in speech transcription related fields an access to transcription tools, that can be used as modular functions. This is the experimental part of the platform.
The deposit of this software at APP is currently being processed.
SPro¶
SPro is a free speech signal processing toolkit which provides runtime commands implementing standard feature extraction algorithms for speech related applications and a C library to implement new algorithms and to use SPro files within your own programs.
The deposit of this software at APP is currently being processed.
Video¶
PyFFas : Python FFmpeg Fast Access Seeker¶
Python FFmpeg Fast Access Seeker is a python module dedicated to frame audio and video access in large collections.
The deposit of this software at APP is currently being processed.
GPUShotFinder¶
Based on GPU NVidia card, this software is video search engine enable to quickly retrieve video shot in a large dataset. It use small and robust frame descriptor that enable to load more than 170 days of video. An HTTP/ResT API is also available.
The deposit of this software at APP is currently being processed.
Multimedia¶
PimPy¶
PimPy for Indexing Multimedia with Python (or Platform for Indexing Multimedia with Python) The aim of this module is to provide a convenient and high level API to manage common multimedia indexing tasks. This project comes from INRIA/IRISA TEXMEX research team works. For more information, see http://www.irisa.fr/texmex/
PimPy allow to :
- retrieve media features, such as :
- video histogram
- binarize dct descriptor
- ...
- detect video cuts
- search a video segment in another video (content based retrieval)
- etc ....
APP deposit: IDDN.FR.001.260038.000.S.P.2011.000.40000
SlideoTracker¶
This software enables to synchronize slides with the corresponding video recording
slideotracker = slides + video + tracking
APP deposit: IDDN.FR.001.100021.000.S.P.2011.000.40000
VidSeg¶
computes video segmentation features such as cuts, dissolves, silences in audio track, changes of ratio aspect, monochrome images.
APP deposit : IDDN.FR.001.250009.000.S.P.2009.000.40000
AVSST¶
AVSST is an Automatic Video Stream Structuring Tool. First, it allows the detection of repetitions in a TV stream. Second, a machine learning method allows the classification of programs and inter-programs such as advertisements, trailers, etc. Finally, the electronic program guide is synchronized with the right timestamps based on dynamic time warping. A graphical user interface is provided to manage the complete workflow.
If you want to cite AVSST in a publication, please use the following reference: AVSST: an Automatic Video Stream Structuring Tool, Zein Al Abidin Ibrahim, University of Caen - Greyc Institute of Research, France
The deposit of this software at APP is currently being processed.
Text¶
KiWi : Keyword Extractor¶
This program seeking to convert an input text into a weighted word vector, usually for document indexing or keyword extraction purposes. More precisely, it implements the TF-IDF (see Salton) method to handle textual documents such as raw text or word meshes and it comes along with various tuning options.
IrisaPhon¶
Software for phonetics of words
IRISA Named Entities¶
IRISA_NE is a couple of Named Entity tagger (based on Ester 2), a tagger is based on CRF and the other on HMM. It is dedicated to the labeling of automatic transcriptions of speech (do not take into account uppercase or punctuation have no concept of sentences). However, they manage texts with punctuation and capitalization eliminated before they pass labellers and render output. The only thing you need to worry about is the character encoding and the tokenization. A log file produced by the tagger tells you unknown words to guide you.
See more details on the author webpage Christian Raymond
Contributions¶
pyleargist : library to compute GIST global image descriptors
- Scikit-Learn
