Transcribing Interviews with Nexus365

Introduction

Recording an interview is convenient way to save notetaking and lets you concentrate on asking questions and responding to the interviewee's answers. Whether offline or online, making a video or audio recording will contain personally identifiable information, even if that is just the voice or face of the interviewee. So you should assume that the recording files are personal data and only store them in suitable secure storage. Transcribing interviews automatically is very powerful and time saving, but it is important that both the recording and transcript are stored and processed in an information security-compliant way. If you are using your mobile device, ensure that you secure it as per these instructions

As the Nexus365 platform has been assessed as secure for all classifications of University data, it is possible to make use of the automatic transcribing feature of Microsoft Stream or Word online to do this at no cost.

Step by step 'how to' guides

Expand All

Word for web (free to use via Oxford's Nexus365 subscription to Microsoft 365) has an automatic transcription feature. This was launched in August 2020 and already offers many advanced features, such as identifying each speaker's voice and labelling the words they say. Currently transcription is only available in Word for web, the feature should be added to the Android and iOS app versions of Word by the end of the year.

You can either make the recording live on your device, or more conveniently upload a recording you made earlier. The live transcriptions are unlimited in length, but when uploading a recording, there is a five-hour limit per user per month and each uploaded recording is limited to 200MB. Currently the only supported language is English, but Microsoft are "working on support for more languages."

Both ways of using this feature are described in detail here or see the introductory video below. 

Install the Stream app on your mobile device – there are apps for both Android and iOS (Apple).

The first screen is the Discover screen, this will show you existing videos which other people in Oxford have shared to the whole organisation. Touch the plus icon on the top righ and select "Create new video":

stream first page2

You will be taken to a video recording screen, similar in functionality to the one your phone came with.

streams recording

Touch the magenta record button at the bottom. Here I am just seeing the notebook on my desk as I am just interested in recording the audio here. I speak into the phone "The quick brown fox jumped over the lazy dog" as an example. To stop recording, press the recording button again (it will show the pause symbol ||).

Press the magenta > button to continue.

after recording2

You can select a subsection of the video to upload on the next screen, or just click "upload". You can now give your recording a file and description. It is also possible to select the language, which should be set to the language spoken in your interview.

streams naming file

Click NEXT. Here you must not change the default "Public within your company" otherwise anyone in Oxford could access the interview!

streams not public

Select the "Video options" submenu where you can check that "Autogenerate captions" is enabled. 

streams autogenerate captions

Press the back arrow at the top left and you should see "completed" at the top of the screen to indicate the video has been uploaded successfully.

stream video published

You will receive an email notification when your video has finished processing, this process could take a few minutes if your video is particularly long. 

Press "DONE" then go to a web browsers on a laptop / desktop computer and go to the Microsoft Streams website.

You may be asked to log in using your SSO details if you are not already logged in to Microsoft.

stream mobile upload on web

Here you can see your recording has been uploaded, with the transcript visible on the right hand side. You should also see "Limited" at the bottom next to your name, indicating that this video is not shared across the whole "company" i.e. Oxford. 

As Stream’s transcription feature is principally designed to improve accessibility and searching of videos (using words in the transcript) it is necessary to modify an audio-only file to allow it to be uploaded to Stream. If you don’t do this, and attempt to upload an MP3 file for example, it will be rejected as an unsupported format. To convert an audio file into a video file, see the instructions “Converting your audio recording into a video file which Stream accepts” below. 

You can check the limits on the number of videos for Stream, but this was 5,000 per user at the time of writing which should be sufficient for most research projects.

Go to the Microsoft Streams website select “+ Create” then “Upload video”:

screenshot showing upload video menu

Select a suitable video file containing your interview recording as the audio track. By default, the videos are kept private to your user account only. Make sure you do not click the “make video available to my organisation” as this will publish the video to the whole University! 

It will take a few minutes to process the video, you will receive a notification when it is finished.  

Once the processing is complete, go to “My content” and select the video. If your window is wide enough, you will see the Transcript on the right of the video:

screenshot showing the Stream video after upload

You can listen to the recording in Stream to check that the transcription is accurate. You can correct any sections which are incorrect using the pencil icon next to the “Search transcript” box. It is easy to edit the transcript here, as you can easily replay any sections where the audio isn’t clear and correct them in place.  

To download the whole transcript in one file: below the video portal is a “Details” tab. Click on the ellipsis (three dots) icon to the right of the heart icon.  Select “Update video details” 

screenshot stream update video details
screenshot stream video details

In the right-hand column, called “Options” there is a link called “Download file” next to Captions.  

When you click this, a file will be downloaded in Web VTT format. This format is useful in that it stores a timecode next to each sentence and will give the Confidence figure for each phrase in the transcribed text. There are tools available which will strip these timecodes and metadata out, if you don’t want it.  

There are several tools which could do this – here we will show you a method using Microsoft Photos which is an app built-in to Windows 10. 

screenshot stream launching photos

Click on the three dots to the right of the screen and select “New video project”

screenshot stream menu

Next give your new video a name: 

screenshot stream new video

Next we need to add a photo to the Project Library in order to add it to the new video project:

stream add photo to library

Pick any image file you like – this will be uploaded to Steam as the video, here I have used the IT Services logo. Then click select the image using the checkbox in the top right corner, and click the three dots, and select “Place in the storyboard” from the menu. 

screenshot stream select image for storyboard

You should now see the image placed in the video preview section of the window on the right: 

stream image in storyboard

Click the “Duration” button and set the duration to the number of seconds. So if your audio recording is 38 minutes long, that is 38 x 60 = 2280 seconds.

stream duration

Now click “Custom audio” above the video preview window: 

stream select custom audio

Add your recorded interview by clicking “+ Add the audio file” and select your audio file. It will appear on the right-hand side of the window. Then drag out the blue bookend sliders to ensure that the whole of your audio recording is included (this is why the duration of the video needs to match).

stream audio track appears right

Click the “Done” button to return to the main window. 

So we now have a video project which contains an image to which will create a Streams-compatible video file, and your audio file as the “custom soundtrack”. Click “Finish Your Video” - choose the low video quality as it saves space and speeds up the upload process. 

stream finish your video

Click “Export” and save the file to a location ready for upload to Stream. Note the file extension is now MP4 signifying a video file.  

stream save as mp4

Click Export, it will take a few minutes if your recording is long: 

stream exporting

This will result in an MP4 file ready to upload to Streams for transcribing - see "Uploading a video in the web version of Stream" above.