大象传媒

Using Gen AI to add subtitles on 大象传媒 Sounds

Subtitles and transcripts generated by AI will be added to a select range of audio content on 大象传媒 Sounds as part of a trial

Aniruddh Dimri

Head of product, 大象传媒 Sounds
Published: 29 August 2024
大象传媒 is written in black text on white boxes while sounds is written in orange text on a black background

A crucial part of the 大象传媒鈥檚 mission is that everyone across the UK feels the 大象传媒 is for them. Sometimes that鈥檚 about the content reflecting our different backgrounds, interests, and identity but it鈥檚 also about ensuring everyone can access our content.

As an example, 大象传媒 Sounds currently produces approximately 27,000 hours of content per month 鈥 but much of it can be difficult to access for the approximately who are deaf, have hearing loss or tinnitus in the UK. We have been exploring ways to add subtitles so people can follow the audio with the help of text.

Doing this manually would be time consuming and prohibitively expensive.

However, as we pilot new technology and explore how we can work with and use to benefit our audiences, we have been looking at whether AI can help us add high quality, accurate subtitles to our audio content.

A screenshot of the Gen AI subtitle on the 大象传媒 Sounds website. Under the 大象传媒 Sounds website header, and episode of Sporting Witness is playing. Subtitles appear above the play button with a transcript of the audio episode.

We have been using a speech-to-text AI tool called Whisper AI, to quickly generate a high-quality transcript of the audio. This is reviewed by a member of the editorial team, and edited where necessary. A final transcript can then be uploaded with the audio on 大象传媒 Sounds.

Today we鈥檙e starting to make this trial public. For the next three months we鈥檒l be running a limited trial in which we鈥檒l add subtitles and transcripts to a select range of audio content for the first time on 大象传媒 Sounds. This trial begins today on the web and Android app versions of 大象传媒 Sounds, and will come to iOS in the coming weeks. The programmes included in the trial will be In Touch, Access All, Profile, Sporting Witness and Economics with Subtitles, and we鈥檒l look to add more programmes across the course of the trial. After the three-month trial period we鈥檒l review progress and determine the next steps.

The way it works is that on the web version of 大象传媒 Sounds, when playing programmes in the trial users will now see a new 鈥渟ubtitles鈥 button in the play bar on the right hand side next to the settings and speed buttons. This looks the same as our accessibility icon on 大象传媒 iPlayer. Pressing this icon will make subtitles appear on screen, showing the words being said as they鈥檙e spoken just as they would on TV or 大象传媒 iPlayer.

Two screenshots of the Gen AI subtitle on the 大象传媒 Sounds app. On the left: an episode of Economics with Subtitles plays on the app. On the right: a transcript of the episode fills the screen.

On the 大象传媒 Sounds app users will see the same icon, this time under the play button. Pressing this will open a timed, full transcript of the full episode 鈥 which highlights the words being said as they鈥檙e spoken, and dynamically follows the text through the episode 鈥 a bit like how it looks when you follow the lyrics in some music apps.

As mentioned 鈥 after three months we鈥檒l review the progress made in the trial, how well the tools are working and if they鈥檙e a cost effective way of making transcripts available in Sounds. After that review, we鈥檒l determine whether or not to continue, and if successful whether to roll them out to more of our content on 大象传媒 Sounds, and potentially to expand to our archive as well.

Search by Tag:

Rebuild Page

The page will automatically reload. You may need to reload again if the build takes longer than expected.

Useful links

Theme toggler

Select a theme and theme mode and click "Load theme" to load in your theme combination.

Theme:
Theme Mode: