AARDVARC

Automatically Annotated Repository of Digital Audio and Video Resources Community

Schedule of the Ypsilanti meeting
(preliminary version; subject to change)


Wednesday, May 9

Informal meeting at
Palm Palace (next to the hotel, map) from 7 PM


Thursday, May 9

Morning session in room 352

8:45 Registration

9:00--9:15 Opening

9:15--10:00 GARY SIMONS Overview: Requirements for implementing the AARDVARC vision. [Abstract][PowerPoint][PDF-slides]

10:00--10:45 MARK LIBERMAN Overview: Processes and tools for speech transcription and annotation. [Abstract]

10:45--11:00 Coffee break

11:00--11:45 SHRI NARAYANAN Automatic extraction of human-centric information from audio-visual resources. [Abstract] [Slides]
12:30--2:00 Lunch at the Lake House

2:00--3:15 Software/project demonstrations (room 352)

MIETTA LENNES
[Abstract] [Slides]

GREG HEDLUND The Phon Project
[Abstract]

BRIAN CARPENTER The APS's audio repository
[Abstract]

ERIC VATIKIOTIS-BATESON FlowAnalyzer: A Tool for Video-Based Motion Analysis
[Abstract]

ROBERT McGRATH Ethnobotany Workbook
[Abstract]

CHRISTIAN DiCANIO, DOUGLAS H. WHALEN, JONATHAN D. AMITH From Mixtec language documentation to phonetic documentation [Abstract]

3:15--4:00 Work in groups

Group 1: USE CASES (room 304)

Develop use cases for a repository of audio and video data: how would speech corpora be used in different disciplines? Are there specifications which such corpora must meet in order to be useful?

Group 2: LEGAL AND INTELLECTUAL PROPERTY RIGHTS (room 350)

Identify the legal and intellectual property rights issues that the repository design must address. Evaluate different ways the repository might handle these issues.

Group 3: ADMINISTRATIVE STRUCTURE AND SELF-SUSTAINABILITY (room 301)

What should the administrative structure of such an archive be? Who should govern it? What conditions should be specified for corpus sharing? How can such an archive be developed to be self-sustaining?



4:00--4:15 Coffee break

4:15--5:15 Work and discussion in groups (continuation)




Friday, May 10

Morning session in room 352

9:00--9:45 PAUL BOERSMA Segmentation and pre-processing of the speech signal. [Abstract]

9:45--10:30 TANJA SCHULTZ Speech recognition in under-resourced languages. [Abstract]

10:30--10:45 Coffee break

10:45--11:30 JEROME CROWDER Audio and video archives for anthropologists. [Abstract]

11:30--12:15 ARIENNE DWYER Audio and video archives for documentary linguists [Abstract] [Slides]

12:30--2:30 Lunch in the Lake House

2:30--4:00 Work in groups

Group 1: SURVEY OF THE EXISTING DATA (room 304)
Revue the results of the survey on existing data from understudied languages and cultures. Report on the amount of data and the most common formats and tools employed. If possible, make a recommendation about the data formats that the repository should support, and note any anticipated problems.

Group 2: ANNOTATION/TRANSCRIPTION PRACTICES (room 352)
Download the annotation samples from different disciplines which are available at [link will be available soon]. Compare the annotation systems and content foci in order to determine the consequences, if any, of different choices of annotation tools. How difficult would it be to switch from these systems to one of the systems used for automatic speech recognition?

Group 3: VIDEO PROCESSING (room 350)
What are the special requirements of video processing? What types of content focus are common? What is annotated, and how? Should audio and video corpora be part of the same repository?


4:00--4:15 Coffee break

4:15--5:15 Work in groups (continuation)

7:00 Conference dinner at Café Felix in Ann Arbor (map)




Saturday, May 11


9:00--9:20 USE CASES: Group report and discussion

9:20--9:40 LEGAL AND INTELLECTUAL PROPERTYRIGHTS: Group report and discussion

9:40--10:00 ADMINISTRATIVE STRUCTURE AND SELF-SUSTAINABILITY: Group report and discussion

10:00--10:20 SURVEY OF THE EXISTING DATA: Group report and discussion

Coffee break

10:50--11:10 ANNOTATION/TRANSCRIPTION PRACTICES: Group report and discussion

11:10--11:30 VIDEO PROCESSING: Group report and discussion

11:30--12:15 Panel Discussion: the way to the automatic annotation, how far are we from the goal? What are the short-term goals in achieving the ultimate goal of an automatic speech recognition/annotation system?