Label speakers in the transcript | Voters

Label speakers in the transcript

under review

Karin

It would be very helpful if Heidi could label speakers in the transcript ("Speaker 1", "Speaker 2" etc) as it is quite time consuming going through the transcript afterwards and having to figure out when I spoke vs when the patient spoke.

Tom

Just for some context on this one, the reason we don't do it today is because the outputs are consistently better if we don't separate them, because any error in the separation/diarisation of speakers is fully trusted by Heidi and leads to worse outputs very often. Basically the convenience of the speaker labels is outweighed by the rate of error in labelling correctly. But we understand the need, we're investigating ways to do it that don't regress the note quality, thanks for all your comments.

Ladan shaikh

I agree with most comments. It is crucial for there to be a differentiation with what the patient reports versus our interpretations for the patient and not to confound the two as one is an offering for the client and the other is their experience of the events. In terms of psychotherapy it becomes confusing if these two are not differentiated.

Joe Ormerod

You can ask Heidi in the transcript to change to playwrite format - but this should be the standard format here! It should never have been so jumbled up by default!

Autopilot

Merged in a post:

Automatic speaker identification/diarisation/improved time-stamping

Alexandra Brown

It would be beneficial and good clinical practice, for Heidi to support automatic speaker identification/diarisation/improved time-stamping while generating/within transcripts. I feel that this is important for clarity, accuracy, ease of interpretation and reading, and clinical and defensible documentation. Some similar platforms already offer this feature. I am aware that this is in development, and I am hopeful that this will become available in the near future.

Autopilot

Merged in a post:

Speaker detection

Benjamin van der Woerd

Speaker detection in the audio transcription. it should recognize which statements come from the clinician and which from the patient / family.

Benjamin van der Woerd

Hi Tom, 
I use heidi only in my clinic setting, but I find that sometimes it mixes up statements I make vs. statements the patient makes in terms of quotes that make it into the note and I have to revise or delete. 
There are a lot of times when I will talk in synonyms and make comparison stories about something relatable so that the patient can understand, but I wouldn't speak to another clinician like that. 
I think it would be nice to be able to "include / exclude" quotes from the clinician.

Tom

Great to hear your perspective, Benjamin van der Woerd! I have a few more questions for you:

What specific scenarios or use cases do you envision where speaker detection would be most beneficial?
Are there any specific accuracy requirements or thresholds for the speaker detection feature?
Would you like the speaker detection feature to be customizable or have any specific settings?

Nayan Patel

I use 2 microphones 1 for me and 2nd 1 for the patient to help distinguishing clearly each speaker. Having tried Otter first this was very easily and clearly identified

Anya Sharma

marked this post as

under review

natalie kowadlo

Agreed! I believe that Otter, an alternative transcription and note taking service can name the speakers in the transcript.

→