Searching information in a collection of video-lectures Marco Ronchetti Giuseppe Riccardi Angela Fogarolli Dipartim. Infor...
What do we need e-learning for? <ul><li>Help traditional students </li></ul><ul><ul><li>e.g. provide learning material on-...
What do we need e-learning for? <ul><li>Help traditional students </li></ul><ul><li>Support remote students </li></ul><ul>...
Traditional and remote students: how? <ul><li>Traditional lecturing is dead. </li></ul><ul><li>The lecture model is under ...
Traditional and remote students: how? <ul><li>…  what is going on in  your classroom? </li></ul><ul><li>At our place, we s...
Breaking the space-temporal unit <ul><li>Can we  free  the student from  </li></ul><ul><li>spatial  and  temporal  constra...
Logical  Architecture Synchronous ( webcast ) Asynchronous  ( On line , or  download - podcast ) Asynchronous( CD - DVD )
Our requirements <ul><li>the lectures should be  easily browsed , with some form of indexing and a direct access to any ti...
Our requirements <ul><li>impact on lectures  should be minimal; </li></ul><ul><li>production costs should be minimal , so ...
System  Architecture OnStage Web Server Video Streamer DVD Browser LODE acquisition
End user requirements <ul><li>Windows: </li></ul><ul><ul><li>Internet Explorer or Mozilla Firefox </li></ul></ul><ul><ul><...
Cognitive interface <ul><li>The main focus is on  the projected slide ,  </li></ul><ul><li>a  clear voice  is very importa...
LODE: the user interface
New Flash version
Lode - portability Supporto della didattica tradizionale Mac – Win - Linux Player MP4 (no slides yet) Presently attempting...
Acquisition - User interface
Acquisition setup
Our experience <ul><li>Over three years: we recorded </li></ul><ul><li>Eight  50 hours courses for the basic level </li></...
Student feedback <ul><li>Enthusiastic .  </li></ul><ul><li>We were “forced” to extend the experiment to a second course! <...
Advantages from student’s perspective <ul><li>Better time management: </li></ul><ul><ul><li>ability to  recover lectures l...
Other advantages <ul><li>Miscellaneous </li></ul><ul><ul><li>perception by the student of a better service provided by the...
Can we do more? <ul><li>Scenario: </li></ul><ul><li>Thousands of recorded lectures. </li></ul><ul><li>Can we dig in them t...
Needle - search results
Needle - architecture ASR Multimodal search!
Needle - ASR  <ul><li>We used 2 ASR: </li></ul><ul><li>A) a speaker independent research system, used for transcriptions o...
Needle - Vocabulary  Research system vocabulary contained 62,879 words Manual transcription contained 702 terms - 57 not p...
ASR - is it good?  For information retrieval - yes. Rare false positive on interesting domain!
Conclusion <ul><li>We have explored the possibility of breaking the space-time constraints of the traditional classroom, a...
Conclusion: the future <ul><li>Further developments </li></ul><ul><ul><li>Semantic indexing of the content </li></ul></ul>...
Upcoming SlideShare
Loading in …5
×

Searching information in a collection of video-lectures

1,039 views
991 views

Published on

Published in: Business, Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,039
On SlideShare
0
From Embeds
0
Number of Embeds
47
Actions
Shares
0
Downloads
23
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Searching information in a collection of video-lectures

  1. 1. Searching information in a collection of video-lectures Marco Ronchetti Giuseppe Riccardi Angela Fogarolli Dipartim. Informatica e Telecomunicazioni Universit à di Trento Italy
  2. 2. What do we need e-learning for? <ul><li>Help traditional students </li></ul><ul><ul><li>e.g. provide learning material on-line </li></ul></ul><ul><li>Support remote students </li></ul><ul><li>Make some activity faster </li></ul><ul><ul><li>e.g. semi-automatically grading tests </li></ul></ul><ul><li>Change the way we teach </li></ul><ul><ul><li>Make it more collaborative </li></ul></ul><ul><li>Create a business </li></ul><ul><ul><li>Get new markets (e.g. Athabasca) </li></ul></ul><ul><ul><li>Sell content (e.g. SCORM lectures) </li></ul></ul>
  3. 3. What do we need e-learning for? <ul><li>Help traditional students </li></ul><ul><li>Support remote students </li></ul><ul><li>Make some activity faster </li></ul><ul><ul><li>e.g. semi-automatically grading tests </li></ul></ul><ul><li>Change the way we teach </li></ul><ul><ul><li>Make it more collaborative </li></ul></ul><ul><li>Create a business </li></ul><ul><ul><li>Get new markets (e.g. Athabasca) </li></ul></ul><ul><ul><li>Sell content (e.g. SCORM lectures) </li></ul></ul>
  4. 4. Traditional and remote students: how? <ul><li>Traditional lecturing is dead. </li></ul><ul><li>The lecture model is under attack by people proposing learner centered learning </li></ul><ul><li>E-learning is an opportunity for a change </li></ul><ul><li>However… </li></ul>
  5. 5. Traditional and remote students: how? <ul><li>… what is going on in your classroom? </li></ul><ul><li>At our place, we sometimes use a blended approach, much stuff is available through the net, </li></ul><ul><li>but the classroom is still there… </li></ul><ul><li>Can we make it any better, while the old paradigm still survives? </li></ul>
  6. 6. Breaking the space-temporal unit <ul><li>Can we free the student from </li></ul><ul><li>spatial and temporal constraints? </li></ul><ul><li>Classical solutions: </li></ul><ul><li>Paper-based learning material </li></ul><ul><li>VHS cassettes (and TV or satellite broadcasting) </li></ul><ul><li>Video distribution through the Internet was not feasible (at least in Europe) until recently </li></ul><ul><li>Video is costly . Video is boring! </li></ul><ul><li>Alternative: podcast - vodcast </li></ul>
  7. 7. Logical Architecture Synchronous ( webcast ) Asynchronous ( On line , or download - podcast ) Asynchronous( CD - DVD )
  8. 8. Our requirements <ul><li>the lectures should be easily browsed , with some form of indexing and a direct access to any time-location in the lecture; </li></ul><ul><li>lectures should be visible on all major platforms (Windows/Linux/Macintosh) </li></ul><ul><li>lectures should be available (in some form) also to students who do not have a large band Internet connection ; </li></ul>
  9. 9. Our requirements <ul><li>impact on lectures should be minimal; </li></ul><ul><li>production costs should be minimal , so as to allow scaling the approach to most courses. </li></ul><ul><ul><li>Set-up must be lightweight! </li></ul></ul><ul><ul><li>Operations must be simple (low level skills!) </li></ul></ul><ul><ul><li>Post-processing operations must be light (i.e. almost automatic), and not require much work </li></ul></ul>
  10. 10. System Architecture OnStage Web Server Video Streamer DVD Browser LODE acquisition
  11. 11. End user requirements <ul><li>Windows: </li></ul><ul><ul><li>Internet Explorer or Mozilla Firefox </li></ul></ul><ul><ul><li>Java and Javascript must be enabled </li></ul></ul><ul><ul><li>QuickTime plug in </li></ul></ul><ul><li>Mac OsX: </li></ul><ul><ul><li>Mozilla Firefox </li></ul></ul><ul><ul><li>Java and Javascript must be enabled </li></ul></ul><ul><ul><li>QuickTime plug in </li></ul></ul><ul><li>Linux: </li></ul><ul><ul><li>No QuickTime plug in available! </li></ul></ul><ul><ul><li>Partial support </li></ul></ul>
  12. 12. Cognitive interface <ul><li>The main focus is on the projected slide , </li></ul><ul><li>a clear voice is very important, </li></ul><ul><li>the video carries additional information like gestures , and can show the environment just enough </li></ul><ul><li>Navigation is possible </li></ul><ul><li>It must be also possible to use the blackboard! </li></ul>
  13. 13. LODE: the user interface
  14. 14. New Flash version
  15. 15. Lode - portability Supporto della didattica tradizionale Mac – Win - Linux Player MP4 (no slides yet) Presently attempting a port to mobile phones
  16. 16. Acquisition - User interface
  17. 17. Acquisition setup
  18. 18. Our experience <ul><li>Over three years: we recorded </li></ul><ul><li>Eight 50 hours courses for the basic level </li></ul><ul><li>Large number of students (over 100) </li></ul><ul><li>Two 50 hours courses for the master level </li></ul><ul><ul><li>International students (Erasmus Mundus Program) </li></ul></ul><ul><li>Six 20 hours international summer schools and workshops held in Italy and Spain </li></ul><ul><li>We will use the system for a EASTWEB Autumn School in Korea in November 2007 </li></ul>
  19. 19. Student feedback <ul><li>Enthusiastic . </li></ul><ul><li>We were “forced” to extend the experiment to a second course! </li></ul>75% anticipated using the system often or very often 5% 63% total 2 nd exam (23 stud.) 1 st exam (45 stud.) students who… 4% 6% … followed the course completely off-line 87% 51% … used the system to review at least one lecture
  20. 20. Advantages from student’s perspective <ul><li>Better time management: </li></ul><ul><ul><li>ability to recover lectures lost due to forced absence (illness, work or other time-frame incompatibility); </li></ul></ul><ul><ul><li>ability to better organize their time , deciding not to be present at some lecture (elective absence); </li></ul></ul><ul><li>Better understanding </li></ul><ul><ul><li>review some critical point (cases of poor understanding of a section due to concentration drop, excessive speed in an explanation or intrinsic difficulty); </li></ul></ul><ul><ul><li>ability to check the correctness of notes taken during a lecture; </li></ul></ul>
  21. 21. Other advantages <ul><li>Miscellaneous </li></ul><ul><ul><li>perception by the student of a better service provided by the university ; </li></ul></ul><ul><ul><li>support foreign (italian) students who might have difficulties with the Italian (English) language ; </li></ul></ul><ul><ul><li>enrichment of the e-learning portfolio; </li></ul></ul><ul><ul><li>possibility for the teacher to view himself; </li></ul></ul><ul><ul><li>possibility to reuse lectures (across time, or in different contexts!) </li></ul></ul>
  22. 22. Can we do more? <ul><li>Scenario: </li></ul><ul><li>Thousands of recorded lectures. </li></ul><ul><li>Can we dig in them to extract material for (less formal) learning? </li></ul><ul><li>Cfr. approach by Mike Wald </li></ul><ul><ul><li>(subtitling for accessibility) </li></ul></ul>
  23. 23. Needle - search results
  24. 24. Needle - architecture ASR Multimodal search!
  25. 25. Needle - ASR <ul><li>We used 2 ASR: </li></ul><ul><li>A) a speaker independent research system, used for transcriptions of the Italian parliament </li></ul><ul><li>B) a commercial (dictation) system </li></ul><ul><li>A) gave 60% word accuracy on sample </li></ul><ul><li>B) gave 76,6% word accuracy (after speaker training, in simulated environment) </li></ul><ul><li>Why so bad? Mike, but not only… </li></ul>
  26. 26. Needle - Vocabulary Research system vocabulary contained 62,879 words Manual transcription contained 702 terms - 57 not present in vocabulary 36 were technical terms Rest was english or spanish words, company names, other minor stuff (re-…, diminutives). Language model is important! We took Java books (11,443 terms before stemming - added to the vocabulary and decreased the unrecognized words from 8% to 3%)
  27. 27. ASR - is it good? For information retrieval - yes. Rare false positive on interesting domain!
  28. 28. Conclusion <ul><li>We have explored the possibility of breaking the space-time constraints of the traditional classroom, and doirectly accessing info by searching </li></ul><ul><li>Validation of the idea: </li></ul><ul><ul><li>See talk at 4:30 in Junior Ballroom A </li></ul></ul>
  29. 29. Conclusion: the future <ul><li>Further developments </li></ul><ul><ul><li>Semantic indexing of the content </li></ul></ul><ul><ul><li>Video editing </li></ul></ul><ul><ul><li>Tighter integration within a collaborative environment </li></ul></ul><ul><ul><li>Add other sources for multimodal search (IWB, annotation…) </li></ul></ul>

×