Automatic subtitling of assembly sessions for WebTV

Transcription and translation

Italy - Chamber of Deputies

Use case ID: 003

Author: IT Department, Chamber of Deputies of Italy

Date: 22 May 2024

Objective: 

Produce, in real time, the subtitles of speeches during assembly sittings. The subtitles are embedded inside the video signals published by WebTV.

Actors: 

  • ASR subtitling system
  • WebTV users

Prerequisites:

  • Existence of an audio signal of assembly speeches
  • Existence of a video signal of the assembly
  • Existence of a pre-trained subtitling model

Scenario:

  1. The audio signal of assembly speeches flows into the ASR subtitling system in real time.
  2. The ASR subtitling system produces the subtitles in real time without human intervention.
  3. The subtitles are embedded with the video signal of the assembly.
  4. The video signal is shown on WebTV. Users can enable/disable the subtitles.

Expected results:

  • The subtitles of assembly speeches are produced in real time and without human intervention, so they can be shown on WebTV.

Potential challenges:

  • ASR model not properly trained
  • The ASR model might not work well with dialects and specific terms not used during the training phase (e.g. the term “COVID-19” was used a lot during the pandemic period, but it was unknown before)

Data requirements:

  • The ASR model should be trained on a large dataset of verbatim reports of sittings. In general, it should be trained on a large dataset of speeches and words in the desired language.

Integrations with other systems:

  • System that produces the audio signal of the assembly
  • System that produces the video signal of the assembly
  • WebTV

Success metrics:

  • Time needed to produce the subtitles
  • Delay between the audio/video signal of the assembly and the corresponding subtitles

 

The Use cases for AI in parliaments collection is published by the IPU’s Centre for Innovation in Parliament as part of the Parliamentary Data Science Hub’s project to create guidelines for AI governance in parliaments.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International licence. It may be freely shared and reused with acknowledgement of the author and the IPU. 

A use case describes how a system should work. It is used to plan, develop and measure implementation. A use case is not the same as a case study, which is a descriptive text of an actual project’s implementation. Please note that this use case is provided “as is” and neither the IPU nor the author accepts any responsibility for its use.

For more information about the IPU’s work on artificial intelligence, please visit www.ipu.org/AI or contact [email protected].