AI-powered, automated, and super-accurate speech recognition infrastructure tool for all of your audio and video data.
Made with ❤️ and ☕ in Bucharest
Transcribing audio to text, the process of converting audio to text, is a time-consuming but essential step in qualitative research. Mercury Research used to do this tedious process manually, with hired 3rd parties.
“I usually moderate two to three hours of group discussions or in-depth interviews for each project I carry on. After moderation, we were waiting for the manual transcription, which took two to three days. This method took a lot of time during the reporting period.”
The company's previous method of transcribing focus group discussions and in-depth interviews was time-consuming and inefficient. They would have to wait for the transcripts to be completed, which could take several days. This delayed the analysis process and prevented the company from sending the final report to clients as quickly as possible.
To address this issue, the company decided to invest in an automated transcription system. This system was supposed to allow them to transcribe the discussions and interviews quickly and accurately. The transcripts would be available immediately, so the company could start the analysis process right away. This would allow them to send the results to clients much faster than before.
The main objectives were to:
Automate the transcription process and provide a faster and more accurate transcription of all the discussions taking place in a focus group or in-depth interview project
Improve work productivity by reducing the time needed for sending the final report to clients, as the manual transcription process took an average of 4 hours per 1 hour of audio recording.
Vatis Tech achieved a transcription speed of approximately 15% of the file length, which means that one hour of audio could be transcribed in less than 10 minutes. This was achieved through the use of advanced speech-to-text technology, with transcripts reaching a high accuracy rate, comparable to the accuracy of human transcription.
The team implemented speaker diarization technology for recordings shorter than 2 hours, to identify multiple speakers throughout an audio-video file. As a result, the transcribed texts had diacritics, could be divided into paragraphs, predefined time sequences, or multiple speakers.
By automating the transcription process, the company was able to:
Reduce the time it takes to transcribe a document from 4 hours needed to manually transcribe 1 hour of audio, to just a few minutes.
Deliver the final reports to their clients faster.
Free up staff time to focus on other tasks, such as creating new content or managing the website.
With a transcription speed of approximately 15% of the file length, the team was able to transcribe 1 hour of audio in less than 10 minutes, helping deliver the transcription faster through its technology.
Vatis' speech-to-text solution automatically reduced work time and helped the team stay focused. The audio/Video is pinned to the text so the team can quickly refer back to the source to check exactly what was said
Reduced the time it takes to transcribe a document from at least 4 hours to just a few minutes.
Researchers and respondents data are fully protected.
Senior Market Research Consultant, Mercury Research