AUDIO & VIDEO ANALYSIS

  • Audio Demux

    1. Version:  2.2.1
    2. Language: C++
    3. Purpose: processing step, separates audio from audio/video stream, resampling
    4. License: GPL (sources available in extractor repository)

  • Speech-to-text (Kaldi)

    1. Version:  2.2.0
    2. Language: Java
    3. Purpose: annotation, transform audio into text annotations
    4. License: ASL2.0 (sources available in extractor repository)

  • Speech-to-text (BING)

    1. Version:  1.1.0
    2. Language: Java
    3. Purpose: annotation, transform audio into text annotations
    4. License: ASL2.0 (sources available in extractor repository, MS Bing API access required)

  • Temporal Video Segmentation

    1. Version:  2.2.0
    2. Language: C++
    3. Purpose: shot annotation, shot and key frame extraction
    4. License: Proprietary (FhG,  available on request)

  • Media Quality

    1. Version:  discontinued
    2. Language: C++
    3. Purpose: media quality annotation for different quality features
    4. License: Proprietary (FhG,  available on request)

  • Audio Editing Detection

    1. Version:  2.0.0
    2. Language: C++
    3. Purpose: annotates whether an audio track has been edited / cut or not
    4. License: Proprietary (FhG, available on request)

  • Media Info

    1. Version:  2.0.0
    2. Language: C++
    3. Purpose: annotation of technical media metadata (container, codec)
    4. License: ASL2.0  (sources available in extractor repository)

  • MediaTags2rdf

    1. Version:  0.9.0
    2. Language: Java
    3. Purpose: annotation helper for Media Info extractor
    4. License: ASL2.0  (sources available in extractor repository)

  • Speech Music Discrimination

    1. Version:  discontinued
    2. Language: C++
    3. Purpose: annotation whether an audio track contains speech or music
    4. License: Proprietary (FhG, available on request)

IMAGE ANALYSIS

TEXT ANALYSIS