Opening Up IIHS Video with SpokenMedia

Editor's Notes

1. Citation: Muramatsu, B., McKinney, A., Wilkins, P. (2010). Opening Up IIHS Video with SpokenMedia. Presented at OpenCourseWare Consortium Global 2010: Hanoi, Vietnam, May 7, 2010. Unless otherwise specified, this work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States License
2. Four step process (simple) First we used the SpokenMedia to do automatic transcription. Next we did hand edit and translation steps. Then we created a player for the presentation of the video and transcripts…
3. Demo
4. First we used the SpokenMedia to do automatic transcription.
5. Lecture Transcription Jim Glass and his group have years of research experience for spoken languages Lectures are a different type of spoken language Much of the speech recognition research has focused on real time transcription of news broadcasts, or interactive voice response systems (telephone) Broadcast news has something like 300 unique words in an hour long broadcast Broadcast news is well structured, prepared copy (in studio via teleprompters), clear transitions between speakers, etc. Lectures are conversational and spontaneous Can use highly specialized vocabularies, engineering, physical sciences, mathematics
6. Spoken Lecture Project Supported by iCampus Includes the browser (which was just demo’d) the processor (back end lecture transcription) and a hand workflow to do the processing Approximately 400 hours of video indexed
7. We only used part of the process due to time constraints. Audio separation, speech processing, time-coded transcript, and then presentation through a SpokenMedia player.
8. Next we did hand edit and translation steps.
9. For this demo, we did computer-based automatic transcription, sent a file to IIHS for “editing” that consisted of performing a hand transcription (due to the format we sent, and the low accuracy of the automatic transcription in this case), a time alignment (though I actually feel that it’s “off” or “slow”) and then a hand translation by IIHS.
10. Recognizer Accuracy Base accuracy is approximately 50% (generic domain and speaker models) Increase accuracy with speaker model up to 80-85%, and specific domain model This approach is good for courses with multiple lectures by the same speaker Domain models get more useful as more relevant text documents are indexed (keyword/noun phrase extraction) Initial results indicate that doing one 99% accurate (by hand/manual) transcript can help immensely for additional lectures by the same speaker Better use of limited resources Search accuracy is closer to 90%, searches tend to be for unique words which the processor is better at recognizing
11. Then we created a player for the presentation of the video and transcripts…
12. What we have today It’s not perfect, but a pretty good start Prototype has a number of useful features that demonstrate search interfaces and interaction interfaces
13. Where are we heading? Transition from research project to service Explore new interactions—what we’re calling Rich Media Notebooks
14. Citation: Muramatsu, B., Kumar, M.S., Merriman, J., Wilkins, P. (2010). Project Greenfield: A New Way of Thinking about OpenCourseWare and Open Educational Resources for MIT. Presented at OpenCourseWare Consortium Global 2010: Hanoi, Vietnam, May 7, 2010. Unless otherwise specified, this work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States License