Often, the best improvements to our product come from practical use. That's why we also test our applications first in our own operations before delivering them to customers.

In the case of ours, we received a request from a colleague at MvR Consulting, Afanaisa Martin, to help with processing 30 recorded interviews of about 1 hour each. Here is a short interview with Afanaisa about her experiences.

Have you used transcription software before?

Yes, I had used OneNote for transcribing texts before. I mainly used it for working out Woo processes. It saved a lot of time and energy, but the texts were not good, and it required a lot of editing work. Mainly because OneNote is not as accurate when it comes to the Dutch language and recognizing it; I had to remove a lot of incorrect words. Additionally, you often have to listen to the audio again because the transcript contains too many mistakes.

What are your findings with our transcription assistant?

It worked very well. Within a few hours, I had the mp4 audio files back as a Word document. At least 80% was accurately transcribed, with punctuation, which saves a lot of work. What I also found noteworthy is that in some interviews a lot of English words were used, and these were also well taken over. Making a language choice in advance seems unnecessary, which is often a limitation in other tools.

I was amazed that from reports of about 8 pages, you can also easily have a summary created by the transcription assistant that is truly very good and captures the essence.

What possibilities do you see for using the transcription assistant?

For example, public meetings (government), team meetings, etc. I also see possibilities for bulky Woo documents that can be provided with a short summary on the front page, or for processing interviews, as I mentioned earlier.

How do you see the transcription assistant developing further?

As a digital transition consultant, I am always looking for ways to work efficiently, but it must also be secure. However, the interviews are of course the first step; now follows summarizing the conclusions from the interviews. A step that I want to take first as a consultant, but I am also very curious about what support AI can provide in this regard.

In the next step, my colleagues from MvR DW will look into whether they can extract additional information from the interviews, such as tone of voice (are people positive or negative regarding the discussed topics), which advantages and disadvantages have been mentioned, but we can also extract specific actions that were mentioned from the conversations. With 30 interviews, that can still be done manually, but with large numbers, think of service desk, surveys or reports, that would of course be very interesting. The transcription assistant is just phase 1 of a broader development of tools to assist with work processes. Other areas I am interested in include working on large-scale research within organizations and using the transcription assistant for analyzing qualitative data.

If you have questions about the MvR transcription assistant, you can reach us at info@mvrdw.nl.