Solutions Lab 29: Using AI Voice-Overs to Deliver Lecture Content

In the online teaching environment, it is really important to ensure that our recorded audio-visual materials are accessible; this is important for all students, but especially those with disabilities, learning preferences or language needs. Narrations must be easy to understand and supported, wherever possible, with captioning/transcripts. But when we are working virtually, in our home work spaces, it is not always easy to produce these resources.

In this session, Alan Wong (School of Engineering) showed how he has improved his videos using Amazon Polly – a free service that turns text into life-like speech. Alan co-ordinates a large course (600+ students) and he very successfully employs a range of good online teaching practices (including chunking, flipped classroom and community building approaches). But it was a comment from his daughter about his early video recordings which led him to start experimenting with voice-over apps. In the session Alan also shares his story; he explained how he selected his voice character (‘Matthew’) and how students have reacted to it. He also highlighted some of the practical challenges he has encountered along the way, sharing his advice for anyone interested in using the approach themselves. Finally, reflecting on the improvements in student performance, he will consider the options for continuing and developing the approach in the future.

The video below is a recording of the session Alan conducted, technical glitches and Q&A removed.

Additional Resources

Similar Solutions Lab Sessions

Solutions Lab 10; Twist & Flip: Creating a great  lecture experience online

Readings

Technical resources

  • Amazon Polly – Amazon Polly is a service that turns text into lifelike speech, allowing you to create applications that talk, and build entirely new categories of speech-enabled products. Polly’s Text-to-Speech (TTS) service uses advanced deep learning technologies to synthesize natural sounding human speech. With dozens of lifelike voices across a broad set of languages, you can build speech-enabled applications that work in many different countries.
  • Canvas Studio – Captioning