Configure News Segmentation

To configure news segmentation , follow these steps.

To configure news segmentation

  1. Create a new configuration to send to Media Server with the process action, or open an existing configuration that you want to modify.

  2. In the [Analysis] section, add three analysis tasks. The first should run speech-to-text on an audio track of the ingested video. The second should run text segmentation to group the words extracted by speech-to-text into sentences. The third is the news segmentation task. For example:

  3. Create a new configuration section and configure the speech-to-text task. For information about how to set up speech-to-text, see Speech-to-Text. For example:

  4. Create a new configuration section and configure the text segmentation task. For example:

  5. Create a new configuration section to contain the news segmentation task settings, and set the following parameters:

    Type The analysis engine to use. Set this parameter to NewsSegmentation.
    Input (Optional) The track to process. HPE recommends that you transcribe speech from the audio track of the news broadcast and then group the extracted words into sentences using a text segmentation task. Set this parameter to the result track of the text segmentation task.
    IdolHost The host name or IP address of the IDOL Server (Content component) to use for news segmentation.
    IdolPort The ACI port of the IDOL Server (Content component) to use for news segmentation.
    MaxStoryDuration The maximum duration of a video segment that can be classified as a story. If a story exceeds this duration, Media Server begins a new story regardless of whether the concepts in the video have changed.

    For example:


    For more information about the parameters that you can use to configure news segmentation, refer to the Media Server Reference.

  6. Save and close the configuration file. HPE recommends that you save your configuration files in the location specified by the ConfigDirectory parameter.