Progress of Interspeech 2005 Information Line

1
Progress of Interspeech 2005 Information Line

• By Team Infoline
• April 24, 2006

2
Speech Recognizer and Robust Parser

• Speech Recognizer
• Challenging Situation
• No Training data,
• Names are there.
• Temp Solution
• New Language Model is trained based on generated
  corpora
• Significantly trimmed down the number of authors
  to recognize (From 200 to 30)
• Few author names are easily recognized still.
• Robust Parser
• Loosen up to deal with irregularities of SR output

3
DM

• Allow disambiguation using author name and
  session name
• Taken care of different scenarios of results
• If there is no results,
• Say Sorry and restart.
• If there is one result
• Present the detail of the paper,
• Then ask whether to present the abstract of the
  paper
• If there is less than or equal to 5 results
• Tell the user the number of papers found
• Then ask whether to present the summary of the
  paper.
• (List of titles of the paper)
• If there is more than 5 results
• Say sorry

4
Backend and NLG

• Backend
• (may be for this demo only)
• SQL-based
• Could do author-search and session-name-search
• NLG
• Fill in all sorts of prompts
• A lot of Implicit Confirmation and Explicit
  Confirmation are missing
• That caused a lot of in the system

5
Other small things We Hacked Out

• Confidence of The Recognizer
• Audio Server is hacked such that
• We are always confident about the results.
• Annoying restarting issue
• Commented the restarting routine in Windows
• Speech Rec (We really fixed these)
• SVQ could now be used.
• Memory reallocation is fixed

6
Demo

• Scenario
• A user want to know the papers written by
• Alan Black
• Julia Hirschberg and
• Andrew Rosenberg
• What it shows
• How bad recognition is taken care now.
• What happened when the number of answers returned
  are multiple or single.