Skip to content

Latest commit

 

History

History
47 lines (38 loc) · 1.87 KB

lab5.org

File metadata and controls

47 lines (38 loc) · 1.87 KB
Raw

Lab V. Advanced dialogue management

Part 1. Improving your voice interface

In this part of the lab you will need to improve dmAppointment.ts application from Lab II. Create a copy of it dmAppointmentPlus.ts and ‘route’ index.tsx to it. Now you will need to implement some improvements.

Note: try not to copy and paste the same code, use functions to abstract certain blocks.

  1. Make sure that system handles unexpected input (out-of-grammar situations).
  2. A opportunity to say “help” at any point when system is recognising something. You should provide a help message (anything you like) and return the user to the state where they were before asking for help.
  3. In a stepwise fashion change the formulations for your re-prompts in case of noinput (ASR sends NOINPUT) event and out-of-grammar situations.
  4. If the user is silent and not reacting to 3 reprompts, return to the init state.

Part 2. Confidence threshold

  1. Implement confidence threshold for speech recognition of user inputs.
    If
    the confidence for the top-ranked recognition hypothesis is higher than threshold X
    then
    assume that the speech recogniton is correct is correct and proceed
    else
    ask the user whether the top-ranked recognition hypothesis is what the user wants.
  2. Test the system and adjust the threshold.
  3. Can you implement a similar threshold for natural language understanding? How can it be combined with the ASR threshold? Justify your choice and provide a sketch implementation.

    Note: The system’s grounding question can to be perceptual (“Did you say ‘create a meeting’?”) or semantic (You want to create a meeting, is that correct?).

Submission

Redeploy your app to Github pages and submit two links: 1) Github pages URL and 2) URL of your repository.