Open topic with navigation

Extract Speech

You can use CFS and IDOL Speech Server to extract speech from audio and video.

When you index audio and video files, KeyView extracts metadata but cannot process the content. The documents produced by CFS therefore have no content. To enrich these documents, you can send the audio and video files to an IDOL Speech Server. The IDOL Speech Server extracts speech from the audio and adds a transcription to the document content.

To extract speech, use the IdolSpeech import task in CFS. The IdolSpeech task includes the following steps:

1. You identify documents that require speech-to-text processing.

2. (Optional) CFS sends the audio to a Transcode Server. The Transcode Server converts the audio into a format that is accepted by the IDOL Speech Server.

3. (Optional) CFS sends the audio to an IDOL Speech Server to determine the language of the speech.

4. CFS sends the audio to an IDOL Speech Server for transcription. The IDOL Speech Server returns the transcription to CFS.

5. CFS adds the transcription to the document content.

Related Topics

• Identify Documents to Process