Inspiration

  • All the meetings have been moved online and all of us work online. Many meetings are conducted every day and getting the summary of the meeting recorded is a major task and is to take care of by one of the team members. It is always cumbersome to record all the points discussed without missing anything. Most of the time, this is seen as a challenging task and people actually are not interested in recording the meeting summary/minutes. Here, we have provided an intelligent AI-based solution that accepts the MEETING AUDIO file as input and gets the complete summary with the persons identified. The transcripts can be downloaded and we also give you complete statistics about how many speakers are identified, how many transcripts are generated etc.

What it does

  • Upload the Meeting audio file to the interactive system we built. Wait for a few seconds, the complete meeting is analyzed by our system and we generate a transcript that has the summary of the meeting with speakers identified accurately.

How I built it

COVID 19 has made a lot of changes in the way we are working every day. Almost everyone is working from home and meetings all happen over platforms like MS Teams, Zoom, or Google meet. Marking the minutes of the meeting is a very important component in any meetings and everyone needs the same to recall and the clients also need it for the recording purpose. Someone manually always makes a note of the important points and at times, it is going wrong and is cumbersome too. We have used done the Extraction, Speech Segmentation, and Speaker Diarization with the input file. Then, we recognize who the speaker is, what the content is, we generate sequential transcription for every second of the meeting. All these are done with our Intelligent AI approach. We used TensorFlow and deep learning techniques extensively to build this.

Challenges I ran into

  1. Identifying the speaker was a major challenge.
  2. Summarizing the points of the meeting in order was a challenge and needed a lot of effort.

Accomplishments that I'm proud of

  1. Our team is very proud of this as we have definitely eased the task of the MoM and used tech to the best extent possible.

What I learned

  1. Perseverance and Smart Working.
  2. Usage of TensorFlow for voice.

What's next for Meetingzz

  1. To talk to the Zoom or WebEx etc. to see how to do we integrate this as part of their tools.

Built With

+ 101 more
Share this project:

Updates