Dear friends,
We are looking for a speech recognition software that will allow us to automatically code the voice of multiple participants talking in alternating turns.
Basically, we expect the software to
1) differentiate voice of participants from each other and assign a different code to each participant,
2) provide a timeline output that will allow us to quantify the duration and frequency of talk for each participant.
A hypothetical coding output would be like this:
ParticipantA:1
ParticipantB:2
ParticipantC:3
No talk:0
Timeline------------------------->>
2222220111111000000022222233333330000011111000000222
Hi!
The problem you have mentioned above is speaker diarization problem ("who speaks when").
There are some open-source tools like Alize, Lium or Kaldi but their parameters should be carfully tuned for working well on your data...
You may use Raspberry Pi and Zigbee... [1]
or, MacSpeech® Dictate speech recognition software [2]
or, mobile application [3]
Reference:
[1] Younis, S. A., Ijaz, U., Randhawa, I. A., & Ijaz, A. (2018). Speech Recognition Based Home Automation System using Raspberry Pi and Zigbee. NFC IEFR Journal of Engineering and Scientific Research, 5.
[2[ Hon-Anderson, E. (2018). U.S. Patent No. 9,865,263. Washington, DC: U.S. Patent and Trademark Office.
[3] Kovacs, M. D., Cho, M. Y., Burchett, P., & Trambert, M. (2018). Benefits of Integrated RIS/PACS/Reporting Due To Automatic Population of Templated Reports. Current Problems in Diagnostic Radiology.
I think the diarization problem is addressed using independent, directional microphones.
- Badges
- Science topic