Improving the ASR transcription service under Panopto
1. ASR: Add automatic speaker identification to the ASR service
2. ASR: Add dynamic language detection, identification and transcription to the ASR service (not only for a video/audio file, but also for individual sentences spoken in that file).
3. Editor: Add adjustability of window size to the windows in the editor (video and time line windows versus left column windows etc.)
4. Editor > Captions > Establish 2 views: A. Captions (the existing view) B. Transcription
5. Editor > Captions > View B. Transcription: Add free text editor features to this view: speaker / language identifier paragraphs, supporting full text editor shortcut workflows, search and replace, spell check etc.
6. Session > Settings > Captions > Ability to export the free text editor version
Reason for the above requested features:
It will improve the accessibility of Panopto transcriptions, knowing who is speaking.
It will improve automatic processing of files uploaded to Panopto, and next support multi language contexts, such as classes, conferences etc. where several languages are spoken.
It will add a more free and swift text editor to Panopto and extent the use of transcription under Panopto to support not only captions, but also more general purpose analytical work.