Serendipity35

Help!

This is query to all of you reading this blog. Are any of you dealing with anything like this at your school?

We have a professor using video files in his online Biology class (mp4 files). He has a student who has received an accommodation from our disabilities services to have text provided for any audio content in his online classes. Apparently, just having a printed audio transcript is not enough. He needs to provide synchronized text as with closed captioning.

The prof is locked into using these videos as an essential part of the class. We are looking for software which takes pre-recorded audio (in a video file) recognizes speech and transcribes it to text automatically and embeds it into a audio/video file in the same or another format. It’s not just transcription, but it would need to combine voice recognition together with captioning/subtitling features.

We have looked at the usual speech to text software (such as Dragon Dictate) and although that can be tricked into transcribing pre-recorded audio rather than live speech, it doesn't embed the transcriptions into the video at the correct frame locations.

Third party transcription/captioning services (such as tech-synergy.com ) are cost-prohibitive.

Suggestions from other technologists have included using Articulate which provides a transcript but it works through PowerPoint. A colleague at another college suggested Cogi which they said they use for both video and audio, although the website only says audio.

Any suggestions? We can't be the only ones dealing with providing accessible files in this way.