It\nis important for teachers to make a good quality recording and this can be\nachieved by wearing a wireless microphone and adjusting the recording level to\nprovide a good signal to noise ratio. If a teacher uses a fixed lectern\nmicrophone and turns or moves away from the microphone to write on the board or\nwalk around the room then the recorded speech level and signal to noise ratio\nwill decrease. If the lecturer repeats any questions or comments or answers\nfrom the students then the speech of the students does not need to be\ntranscribed. It is also possible to record and transcribe the speech of the\nstudents using a wireless microphone, either handheld or passed around or using\nan app on a mobile phone.<\/p>\n\n\n\n
As\nthe quality of the recording worsens then speech recognition may struggle more\nthan human transcribers and a solution to this problem of improving the\naccuracy of speech recognition transcription is to use students to collaboratively\ncorrect errors. Students correcting errors engage more strongly with the\nlecture content to improve their learning and so justifying the awarding of\nacademic credit for correcting errors. Universities and students could choose\nappropriate rewards.<\/p>\n\n\n\n
Students correcting errors in their own lectures involves little extra effort while they listen, watch, and read the recording and captions as it is difficult not to notice errors. They also generally know the subject better than a professional captioner as captioning companies do not guarantee to provide a specialist in that subject. Images and slides can be automatically synchronised with the transcript to enable printing out of all of the information from a lecture.<\/p>\n\n\n\n
Artificial intelligence machine learning using Deep Neural Networks has proved very powerful for improving the accuracy of speech recognition and recognising images. AI can also be used for enhancing speech recognition through automatic lipreading and can also recognise some sounds on videos for captioning (e.g. Applause, music and laughter). AI can also modify lip patterns and faces on videos to make them easier to lipread.<\/p>\n\n\n\n
AI\ncannot however currently provide automatic audio description of videos as this\nrequires reasoning and understanding subtle meanings and context to identify\nwhat visual information is important. For example in a video if a person leaves\nthe room then while it might be possible for the AI system to identify this had\nhappened this might only be important information to provide in an audio\ndescription if it was necessary for the viewer to know that the person leaving\nthe room could not have heard what was being discussed in the room after they had\nleft the room. <\/p>\n\n\n\n
AI\ncan also provide automatic sign language translation of the captions using\navatars although the quality of translation for a visual language is not as\ngood as translations between written languages which have vast amounts of data\navailable for training the AI systems.<\/p>\n\n\n\n
Mike is one of the keynote speakers at the Media & Learning Conference on Video in High Education and will be speaking on the topic of accessibility on 6 June in Leuven.<\/p>\n\n\n\n
![\"\"](\"https:\/\/media-and-learning.eu\/files\/2019\/03\/Mike_wald_keynote.jpg\")
<\/figure>Author
<\/p>\n\n\n\n
Prof. Mike Wald, University of Southampton, UK<\/p>\n\n\n\n
Mike’s background<\/a><\/p>\n\n\n\n